Page Not Found
Page not found. Your pixels are in another canvas.
Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Page not in menu
This is a page not in th emain menu
Posts
A NeurIPS 2024 Blog: Day 0 & Day 1
Published:
Hello there 👋 Attending large machine learning conferences is both exciting and challenging. They can be expensive and not accessible to everyone, and I’ve certainly felt the fear of missing out when unable to attend in the past.
Introducing mle-monitor: A Lightweight Experiment & Resource Monitoring Tool 📺
Published:
“Did I already run this experiment before? How many resources are currently available on my cluster?” If these are common questions you encounter during your daily life as a researcher, then mle-monitor is made for you. It provides a lightweight API for tracking your experiments using a pickle protocol database
Introducing mle-scheduler: A Lightweight Tool for Cluster/Cloud VM Job Management 🚀
Published:
“How does one specify the amount of required CPU cores and GPU type again?” I really dislike having to write cluster job submission files. It is tedious, I always forget something and copying old templates feels cumbersome. The classic boilerplate code problem. What if instead there was a tool that would completely get rid of this manual work?
All-CNN-C & Centered Kernel Alignment in JAX
Published:
In this blog we implement the Centered Kernel Alignment (CKA) metric used to compare the representations of different neural network layers for the same or two separate networks. CKA measures the similarity of representations at different network layers of the same or different networks.
Introducing mle-hyperopt: A Lightweight Tool for Hyperparameter Optimization 🚂
Published:
Validating a simulation across a large range of parameters or tuning the hyperparameters of a neural network is common practice for every computational scientist. There are a plethora of open source tools that implement individual algorithms, but many of them are either combersome to set up and log or follow diverse syntax, which makes it hard to easily wrap them.
Introducing mle-logging: A Lightweight Logger for ML Experiments 📖
Published:
There are few things that bring me more joy, than automating and refactoring code, which I use on a daily basis. It feels empowering (when done right) and can lead to some serious time savings. The motto: ‘Let’s get rid of boilerplate’. One key ingredient to my daily workflow is the logging of neural network training learning trajectories and their diagnostics (predictions, checkpoints, etc.).
Evolving Neural Networks in JAX
Published:
“So why should I switch from <insert-autodiff-library> to JAX?”. The classic first passive-aggressive question when talking about the new ‘kid on the block’. Here is my answer: JAX is not simply a fast library for automatic differentiation. If your scientific computing project wants to benefit from XLA, JIT-compilation and the bulk-array programming paradigm – then JAX provides a wonderful API.
Meta-Policy Gradients: A Survey
Published:
Most learning curves plateau. After an initial absorption of statistical regularities, the system saturates and we reach the limits of hand-crafted learning rules and inductive biases. In the worst case, we start to overfit. But what if the learning system could critique its own learning behaviour?
The Lottery Ticket Hypothesis: A Survey
Published:
Metaphors are powerful tools to transfer ideas from one mind to another. Alan Kay introduced the alternative meaning of the term ‘desktop’ at Xerox PARC in 1970. Nowadays everyone - for a glimpse of a second - has to wonder what is actually meant when referring to a desktop. Recently, Deep Learning had the pleasure to welcome a new powerful metaphor: The Lottery Ticket Hypothesis (LTH).
A Machine Learning Workflow for the iPad Pro
Published:
The iPad is a revolutionary device. I take all my notes with it, read & annotate papers and do most of my conceptual brainstorming on it. But how about Machine Learning applications? In todays post we will review a set of useful tools & venture into the love story of the iPad Pro & the new Raspberry Pi (RPi).
Getting started with JAX (MLPs, CNNs & RNNs)
Published:
JAX, Jax, JaX. Twitter seems to know nothing else nowadays (next to COVID-19). If you are like me and want to know what the newest hypetrain is about - welcome to todays blog post!
On “On the Measure of Intelligence” by F. Chollet (2019)
Published:
Last week Kaggle announced a new challenge. A challenge that is different - in many ways. It is based on the Abstraction and Reasoning Corpus & accompanied by a recent paper by Francois Chollet.
My Top 10 Deep RL Papers of 2019
Published:
2019 - What a year for Deep Reinforcement Learning (DRL) research - but also my first year as a PhD student in the field. Like every PhD novice I got to spend a lot of time reading papers, implementing cute ideas & getting a feeling for the big questions. In this blog post I want to share some of my highlights from the 2019 literature.
Cognitive Computational Neuroscience 2019 - A Mini-Report
Published:
TL;DR: This blog post provides an overview of trends & events from the Cognitive Computational Neuroscience (CCN) 2019 conference held in Berlin. It summarizes the keynote talks and provides my perspective and thoughts resulting from a set of stimulating days. More specifically, I cover recent trends in Model-Based RL, Meta-Learning and Developmental Psychology adventures. You can find all my notes here.
Forward Mode Automatic Differentiation & Dual Numbers
Published:
Automatic Differentiation (AD) is one of the driving forces behind the success story of Deep Learning. It allows us to efficiently calculate gradient evaluations for our favorite composed functions. TensorFlow, PyTorch and all predecessors make use of AD. Along stochastic approximation techniques such as SGD (and all its variants) these gradients refine the parameters of our favorite network architectures.
A Primer on Deep Q-Learning
Published:
Before starting to write a blog post I always ask myself - “What is the added value?”. There is a lot of awesome ML material out there. And a lot of duplicates as well. Especially when it comes to all the flavors of Deep Reinforcement Learning. So you might wonder what is the added value of this two part blog post on Deep Q-Learning? It is threefold.
EEML 2019 - A (Deep) Week in Bucharest!
Published:
In January I was considering where to go with my scientific future. Struggling whether to stay in Berlin or to go back to London, I got frustrated with my technical progress. At NeuRIPS I encountered so much amazing work and I felt like there was too much to learn until reaching the cutting edge. I was stuck. And then my former Imperial supervisor forwarded me an email advertising this new Eastern European Machine Learning (EEML) summer school.
Representational Similarity - From Neuroscience to Deep Learning… and back again
Published:
In today’s blog post we discuss Representational Similarity Analysis (RSA), how it might improve our understanding of the brain as well as recent efforts by Samy Bengio’s and Geoffrey Hinton’s group to systematically study representations in Deep Learning architectures. So let’s get started!
Steal, Stole, Stolen - A ML Perspective!
Published:
Hola guapos! After finally deciding to stay in Berlin, I felt the desire to structure myself and to establish routines which are going to help me tackle the next phase of my life. Due to a fortunate visit to the National Gallery book store in London, I got to pick up Austin Kleon’s amazing piece of work “Steal Like an Artist”. A beautifully collected and visualized set of tricks to foster creativity.
Barcelona GSE Articles and Interviews
Published:
Hey there! As some of you might know I have been quite actively contributing to the Data Science Barcelona GSE blog. Writing about technical topics and addressing a broad audience is challenging and fulfilling at the same time. I hope that this blog is going to help me learn to tell great narratives and influence people. So stay tuned!
news
I got accepted into the SCIoI Excellence Cluster!
Published:
I got accepted into the Science of Intelligence Excellence Cluster! Starting in October 2019 I will be working on the project “Learning of Intelligent Swarm Behavior” under the supervision of Henning Sprekeler and Pawel Romanczuk. I am very happy to receive such generous funding and support from the excellence cluster.
I will stay affiliated with the Einstein Center for Neurosciences. Furthermore, my work will combine strong evidence from cognitive neuroscience and animal psychology in order to study the computational basis of coordination and adaptation in large collectives.
I will be giving a Talk @ENCODS FENS PhD Symposium!
Published:
I am happy to announce that I will be giving a short talk at the ENCODS FENS PhD Symposium about the “Neural Suprise in Human Somatosensation” project I have been working on during my first ECN lab rotation together with Sam Gijsen, Miro Grundei, Dirk Ostwald and Felix Blankenburg. If you are interested in more details and the general paradigm, check out our GitRepo.
RAAI Conference & EEML - I am coming!
Published:
Bucharest - I am coming! Very happy to attend the Recent Advances in Artificial Intelligence conference from 28th to 30th of June. I will present my work on Deep Multi-Agent RL for swarm dynamics in a poster session. Furthermore, my work has also been selected to be presented at the super-duper awesome EEML summer school. Can’t wait to meet the hero of temporal abstractions Doina Precup and Mr “Policy Distillation” Andrei Rusu.
Kick-Off ‘Flexible Learning’ Reading Group @TUBerlin
Published:
Last week we got to kick-off our new “Flexible Learning” reading group at the Technical University Berlin where we cover recent papers in Meta-/Transfer-/Continual & Self-supervised Learning! We started by reading the latest first-author paper by Yoshua Bengio connecting Meta-Learning with causal inference.
You can join our mailing list for more infos: click here.
Here are all the relevant infos for the next meeting:
- Date: 7th of August
- Time: 11am
- Location: MAR Building TU Berlin - room 5.013
- Paper: “Task-Driven Convolutional Recurrent Models of the Visual System” by Nayebi et al (2018; NeuRIPS)
Massive thanks goes out to the co-organizing help of Thomas Goerttler, Joram Keijser & Nico Roth! Hit me up if you are interested in joining!
Action Grammars are going to CCN!
Published:
Super exciting news! Parts of my masters’s thesis project (supervised by Professor Aldo Faisal) got accepted at the Cognitive Computational Neuroscience conference 2019. We combine Hierarchical Reinforcement Learning & Grammar Induction to define a set of temporally-extended actions… aka an Action Grammar! The resulting temporal abstractions can be used to efficiently tackle imitation, transfer and online learning.
Check out the preprint here! I am still in the process of extending the experiments and already looking forward to the poster presentations in Berlin (13th to 16th of September). The code will be open sourced as well. Hit me up if you are interested in the full story!
OIS Award Final Pitch Selection!
Published:
I am really excited to share that my project proposal on “Deep Swarm Shepherding - Benevolent Adaptation of Collective Behavior” has been selected for the final round of the Open Innovation in Science Award of the Einstein Center for Neurosciences Berlin. The goal of the award is to facilitate projects which fuse Open Innovation and Open Science in the context of neuroscience. It is jointly co-organized by the Ludwig Boltzmann Gesellschaft’s Open Innovation in Science Center (LBG OIS Center), QUEST and SPARK-Berlin.
I am very honored and am looking forward to all the 3 minute pitches! If you are interested in learning more about how I intend to make the world a better place by combining Behavioral Tracking, Inverse Reinforcement Learning and Machine Theory of Mind come by. The final round of the selection process will be publicly carried out - here are all the key information:
- Location: Charité Campus Mitte, Charité CrossOver (CCO), Charitéplatz 1, 10117 Berlin.
- Date and Time: Thursday, October 10, 2019, 16:00-18:15 (official part), doors open at 15:45.
Action Grammars @NeurIPS Workshops!
Published:
Super excited to share that my Master’s thesis project with Aldo Faisal got accepted to both the ‘Deep Reinforcement Learning’ & the ‘Learning Transferable Skills’ Workshop at NeurIPS 2019. I will be presenting the work within the DRL workshop in Vancouver and December!
Check out the updated preprint here & let me know if you have any ideas/questions. Furthermore, code to replicate the results may be found here.
Love, Rob
P.S.: Here is my previous poster from CCN:
Rob joins for.AI 
Published:
I am really excited to announce that I have joined for.AI as an independent researcher. for.AI is a mainly-remote coordinated international group of ML researchers. One aim - the production of useful & effective ML research.
I am very much looking forward to new ideas, enthusiastic discussions and fruitful collaborations 
! Such a great idea for the 21st century!
Love, Rob
P.S.: You can check out my solution to the coding challenge (comparing different pruning techniques) here!
Visual-ML-Notes Launch 
Published:
Really happy to share Visual-ML-Notes ✍️ a virtual gallery of sketchnotes taken at Machine Learning talks 🧠🤓🤖 which includes last weeks #ICLR2020.
Explore, exploit & feel free to share:
website 💻 & the repository 📝
Love,
Rob
P.S.: There will be an entire blogpost dedicated to how I go about sketching, the workflow and the post-processing. Stay tuned
Rob @Virtual MLSS 
Published:
I am really happy to be attending the virtual edition of the MLSS Tübingen summer school where I will be presenting my most recent work on ‘Time Limits in Meta-Reinforcement Learning’. Get in touch if you want to chat about science, arts and ethology! Also I am looking forward to adding a new album to #visual-ml-notes 📝
Love,
Rob
Rob’s 1st Podcast - ML Street Talk 
Published:
Dear virtual world,
Last week I got to do my very first podcast. Exciting, right? I had a great time discussing my journey from Econ to ML & Collective Behaviour, social notions of intelligence & the Lottery Ticket Hypothesis! Thanks for having a podcast newbie! Checkout the full podcast by Tim Scarfe, Connor Shorten and Yannic Kilcher here:
Love,
Rob
Learning not to Learn @MetaLearning NeurIPS Workshop
Published:
I am very happy to be presenting my recent work on “Learning not to learn: Nature versus nurture in silico” at the NeurIPS Meta Learning workshop. We investigate the interplay of ecological uncertainty, task complexity and expected lifetime on the amortized Bayesian inference performed by memory-based meta learners. Checkout the preprint and feel free to drop me a note or hangout at the poster sessions on December, 11th.
Rob @Virtual M2L
Published:
Happy new year! I am really happy to be attending the virtual (and first) edition of the Mediterranean Machine Learning (M2L) summer school. Get in touch if you want to chat about JAX, evolutionary algorithms or meta-learning! And stay tuned for some new #visual-ml-notes 📝 Big thank you to the organizers!
Love,
Rob
Talk @Warwick PhD Statistics Seminar
Published:
I got to give a talk 
about my recent work on meta-learning not to learn at the University of Warwick PhD Statistics Seminar.
You can check out the pre-print here: Link.
Talk @MIT Michael Carbin’s Lab
Published:
I got to give a talk about my recent work on lottery tickets in Deep Reinforcement Learning at Michael Carbin’s lab at MIT. Big thank you goes out to Jonathan Frankle for the kind invitation. This is joint work with my outstanding MSc student Marc A. Vischer and my supervisor Henning Sprekeler. Watch out for the pre-print!
ML Street Talk Episode with Tom Zahavy
Published:
I had the honour to interview Dr. Tom Zahavy in the recent ML Street Talk episode together with Tim Scarfe and Yannic Kilcher. We discuss meta-gradients, JAX and the hardware lottery as well as the state and future of Deep RL. Check out the full episode here:
Rob @Medium TDS Featured Authors Series 
Published:
I had a great time talking to Towards Data Science about my path into Machine Learning. We talk about my transition from Economics to Data Science and Computational Neuroscience. It is an honour to be part of the ‘Featured Authors Series’. You can check out the full Medium interview here!
Lottery Tickets in DRL @NERL ICLR Workshop
Published:
I am very happy to be presenting our recent work “On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning” at the ICLR ‘A Roadmap to Never-Ending RL’ workshop. We investigate the lottery ticket phenomenon in Deep Reinforcement Learning and provide evidence that most of the RL ticket effect can be attributed to the discovered pruning mask. Furthermore, the input layer mask discovered by Iterative Magnitude Pruning yields minimal task-sufficient representations. This mask can be used as a pair of “goggles” that compresses the representation. Dense agents trained on such a representation attain comparable performance at lower computational costs.
Checkout the preprint and feel free to drop me a note or hangout at the poster sessions on May, 7th. This is joint work with the phenomenal Master student Marc Vischer and my supervisor Henning Sprekeler.
Lottery Tickets in DRL @Sparsity in Neural Networks Workshop
Published:
Very happy to be presenting our recent work “On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning” at the Sparsity in Neural Networks Workshop.
Checkout the preprint and feel free to drop me a note or hangout at the poster sessions on July, 8th and 9th. This is joint work with the phenomenal Master student Marc Vischer and my supervisor Henning Sprekeler.
Rob @CCN Algonauts Challenge Talk
Published:
I am very happy to be presenting my 5th place submission to the Algonauts Challenge during the CCN Algonauts workshop next Tuesday (September 7th, 1.30pm UTC-4/EDT). The solution is based on SimCLR-v2 features and a Bayesian Optimization pipeline for the encoding models:
Checkout my challenge report and code repository and feel free to drop me a note. Thank you very much to the organizers and fellow algonauts for this great experience.
Update: You can watch the YouTube replay here:
Swarm Identification @Champalimaud Symposium
Published:
Very happy to be presenting our work-in-progress “SoftEtho: A Gradient-Based Method for Scalable Identification of Ethological Models” at the poster sessions of the Champalimaud Research Symposium. This is joint work with Luis Gómez-Nava, Pawel Romanczuk and Henning Sprekeler. Feel free to drop me a note or hangout at the poster sessions in Lisbon.
‘Learning not to Learn’ Accepted @AAAI2022 🚀
Published:
My very first first author ML conference paper has been accepted at AAAI 2022 🎉! In ‘Learning not to learn: Nature versus Nurture in Silico’ we investigate the interplay of ecological uncertainty, task complexity and the agents’ lifetime and its effects on the meta-learned amortized Bayesian inference performed by an agent. There exist two regimes: One in which meta-learning yields a learning algorithm that implements task-dependent information-integration and a second regime in which meta-learning imprints a heuristic or ’hard-coded’ behavior:
Check out the tweeprint here!
P.S.: Stay tuned for an updated paper version and the release of the open source code.
Received a Google Cloud Research Grant 🎊
Published:
Happy to share that I received a Google Cloud Research Credit Grant to study the intersection of meta-learning and evolution strategies. The grant comes with 1000$ GCP credits and will be well spend on running JAX experiments with TPU acceleration! 🚀
Rob Was Interviewed @TalkRL Podcast
Published:
I had a fun time being interviewed by Robin Ranjit Singh Chauhan for the TalkRL podcast . We discuss my recent papers on meta-learning innate behavior, lottery tickets in Deep RL and my work at the intersection of Hierarchical RL and language (Action Grammars). You can check out the episode here!
Talk @CSHL NeuroAI Seminar 🧑🔬
Published:
I got to give a talk about my work on meta-learning not to learn (accepted at AAAI 2022) at the CHSL NeuroAI seminar invited by Tony Zador.
You can check out the pre-print here: Link.
Can memory-based meta-learning not only learn adaptive strategies 💭 but also hard-code innate behavior🦎? In our #AAAI2022 paper @sprekeler & I investigate how lifetime, task complexity & uncertainty shape meta-learned amortized Bayesian inference.
— Robert Lange (@RobertTLange) December 16, 2021
📝: https://t.co/HPY8xJZkea pic.twitter.com/PuULv87Q4c
‘Lottery Tickets in DRL’ Spotlight @ICLR 2022
Published:
Very happy to share that our recent work “On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning” has been accepted as a Spotlight at ICLR 2022.
Checkout the preprint, the OpenReview discussion and feel free to drop me a note. This is joint work with the phenomenal Master student Marc Vischer and my supervisor Henning Sprekeler.
evosax Release 🎉 - Evolution Strategies in JAX 🦎
Published:
I am more than excited to share that I have just released evosax – a JAX-based library of evolution strategies. evosax allows you to leverage JAX, XLA compilation and auto-vectorization/parallelization to scale ES to your favorite accelerators. The API is based on the classical ask, evaluate, tell cycle of ES. Both ask and tell calls are compatible with jit, vmap/pmap and lax.scan. It includes a vast set of both classic (e.g. CMA-ES, Differential Evolution, etc.) and modern neuroevolution (e.g. OpenAI-ES, Augmented RS, etc.) strategies. 👉 
MLE-Infrastructure Talk @co:here 🎙️
Published:
I got to give a talk about the MLE-Infrastructure at Cohere invited by João Guilherme Araújo.
You can check out a related tutorial here: Link.
evosax Talk @MLC Research Jam 🐘
Published:
I got to give a talk about the evosax at the last ML Collective research jam.
You can check out the recorded talk here:
Rob @Deep Minds 🇩🇪 Podcast
Published:
I had a great time talking about my recent meta-learning research with Max & Matthias from the Deep Minds podcast 🎙
Check out the episode if you are interested in a Machine Learning perspective on the nature-nurture debate 🦎 or if you would like to hear me struggle with talking about my research in German 🇩🇪 (aka out-of-distribution generalization 😋).
Thank you very much for the invitation & thoughtful questions! 🤗
‘Lottery Tickets in DRL’ Talk @DLCT
Published:
I got to give a small talk on our recent work “On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning” (ICLR, 2022) at the Deep Learning Trends and Classics (DLCT) reading group organized by Rosanne Liu and the MLCollective.
Checkout the preprint, the OpenReview discussion and feel free to drop me a note. This is joint work with the phenomenal Master student Marc Vischer and my supervisor Henning Sprekeler.
Rob will be TA @M2L Summer School 🧑🏫
Published:
Excited to share that I will be a teaching assistant at the M2L Summer School this September in Milan! Very much looking forward to teaching the ABC of JAX, to enjoy food, a set of outstanding talks and to give back to the community
Summer Research Internship @DeepMind 🎉
Published:
I am super excited to share that I will be spending the summer at DeepMind working as a Research Scientist Intern. This is an absolute dream come true and I am looking forward to returning to London. I will be hosted by Sebastian Flennerhag and working within the Discovery Team led by Satinder Singh.
gymnax Talk @MLC Research Jam 🏋️
Published:
I got to give a talk about the gymnax at the last ML Collective research jam.
You can check out the recorded talk here:
Research Talk @FLAIR in Oxford 🎙️
Published:
Got to give a talk at the Foerster Lab for AI Research about Evolutionary Meta-Learning.
Research Talk @AIRL at Imperial 🎙️
Published:
Got to give a talk at the Adaptive & Intelligent Robotics Lab about Evolutionary Meta-Learning, gymnax and evosax.
New evosax paper & v.0.1.0 release 🐘
Published:
Super excited to share evosax release v.0.1.0 and an accompanying paper, which covers all the features and summarizes recent progress in hardware accelerated evolutionary optimization! The new additions include:
- Many new evolution strategies including ASEBO, Guided ES, Discovered ES, FR-CM-NES
- Many new genetic algorithms including MR-1/5-GA, SAMR-GA, GESMR-GA
- Wrappers for gymnax-powered fitness rollouts & evosax → EvoJAX compatible strategies
- Improved default hyperparameter settings
- All BBOB benchmarking functions in JAX
- Restart wrappers including IPOP and BIPOP
- Indirect encodings including MLP hypernetworks
Checkout the repository and the arxiv preprint.
Research Talk @Advanced RL Seminar at TU Berlin 🎙️
Published:
Got to give a talk at the Advanced RL seminar at TU Berlin about Evolutionary Meta-Learning, gymnax and evosax.
Research Talk @BLISS Group 🎙️
Published:
Got to give a talk at the BLISS group at TU Berlin about Lottery Tickets in Deep RL and beyond.
Learned ES Accepted @ICLR 2023 🧑🔬
Published:
My DeepMind internship project paper ‘Discovering Evolution Strategies via Meta-Black-Box-Optimization’ got accepted at ICLR 2023. We parametrize the set operation of recombination in ES via a small self-attention layer and meta-learn its weights on a task distribution. The resulting learned ES outperforms several baselines on control tasks. It can be even meta-trained in a self-referential fashion and reverse engineered into an analytical ES!
Check out the preprint and Open Review discussion.
Critical fish shoals published @Nature Physics 🎉
Published:
Our SCIoI collaboration with the lab of Pawel Romanzcuk was published in Nature Physics. In the paper Luis Gomez-Nava and his co-authors analyze the collective diving behavior of fish shoals in Mexico. They find that real-life fish operate close to a phase transition (‘critical point’). Afterwards, they combine Machine Learning techniques and in-silico simulation to analyze the function of this system behavior. They demonstrate that it facilitates optimal information propagation in the face of environment perturbations such as predator attacks.
Check out the paper!
Research Talk @UCL Dark 🎙️
Published:
Got to give a talk at UCL Dark about my internship project on Evolutionary Meta-Learning, gymnax and evosax.
Research Talk @Oxford (AIMS Seminar) 🎙️
Published:
Got to give a talk at Oxford University about our work on sparse trainability in Deep RL and beyond.
Learned GA & evosax @GECCO 2023 🧑🔬
Published:
My DeepMind internship project paper ‘Discovering Attention-Based Genetic Algorithms via Meta-Black-Box-Optimization’ got accepted as a full paper at GECCO 2023. We parametrize the set operations of selection, mutation rate adaptation & sampling in GAs via a small attention layer and meta-learn the weights on a task distribution. The resulting learned GA outperforms several baselines! The preprint can be found here.
Furthermore, the evosax paper write-up got accepted as a poster paper. Very grateful to all reviewers and the open source community feedback.
Summer Research Internship @Google Brain 🎉
Published:
Very excited to share that I will be spending the summer at Google Brain working as a Student Researcher with the Tokyo team. The work by Yujin Tang, Yingtao Tian and David Ha has been really influential and inspired my work on attention-based ES/GA. I can’t wait to do great work – thank you for the opportunity.
🐘 evosax Talk @PyData Berlin 🎙️
Published:
Super excited to give a talk on evosax at this years PyData Berlin conference. Check out the slides below:
🎙️Stocked to present evosax tomorrow at @PyConDE
— Robert Lange (@RobertTLange) April 18, 2023
It has been quite the journey since my 1st blog on CMA-ES 🦎 and I have never been as stoked about the future of evo optim. 🚀
Slides 📜: https://t.co/vw4LTcO1DJ
Code 🤖: https://t.co/ckZsxkLd00
Event 📅: https://t.co/NpZhMa5LmW pic.twitter.com/dg8NNcyzwr
🧬 Learned Evolution Talks @AutoML & @DLCT 🎉
Published:
Super excited to give two talk on discovering new evolutionary optimizers using evolutionary meta-learning at the AutoML Seminar (April 27th) and at the DLCT reading group (April 28th). The talk covers our two recent papers:
Check out the slides below and here:
📝 ‘Lottery Tickets in EvoOpt’ Accepted @ICML 2023 🎉
Published:
Very happy to share that our recent work “Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability” has been accepted at ICML 2023.
Checkout the preprint, the code and feel free to drop me a note.
G-Research Travel Grant Awarded for @GECCO 🎉
Published:
Super excited to have received a G-Research travel grant for attending GECCO 2023 in Lisbon. I will present our work on learned genetic algorithms and the evosax paper write-up as a poster paper. Very grateful G-Research for supporting my work!
📝 ‘NeuroEvoBench’ Accepted @NeurIPS DSB Track 2023 🎉
Published:
Very happy to share that our recent work “NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications” has been accepted at the NeurIPS 2023 Datasets and Benchmarks Track.
Checkout the paper, the code and feel free to drop me a note.
DAAD IFI Scholarship for @Oxford 🎉
Published:
Super excited to have received an IFI DAAD scholarship for visiting FLAIR @University of Oxford for 5 months starting in January, 2024. Very grateful to get this opportunity to finish up my PhD journey.
Update: I unfortunately had to decline the scholarship and joined Sakana.AI as a research scientist and founding member.
🎉 I am a RS & Founding Member @Sakana.AI 🐠
Published:
Super excited to share that I joined Sakana.AI as a research scientist and founding member. I will be working at the intersection of large models and evolution, building a nature-inspired foundation model.
David’s and Yujin’s work has deeply shaped my own research agenda and I am stoked for everything that is still come!
🎉 Stoked to share that I joined @SakanaAILabs as a Research Scientist & founding member.@yujin_tang & @hardmaru's work has been very inspirational for my meta-evolution endeavors🤗
— Robert Lange (@RobertTLange) January 16, 2024
Exciting times ahead: I will be working on nature-inspired foundation models & evolution 🐠/🧬. https://t.co/gCrITNZn97
📝 ‘EvoLLM’ & ‘EvoTransformer’ Papers Are Out 🎉
Published:
Stoked to share that two projects I worked on during my Google DeepMind student researcher time in Tokyo 🗼 are now available on arXiv! We explore the capabilities of Transformers for Evolutionary Optimization.
More specifically, our first work, EvoLLM 💬, shows that LLMs, which were purely trained on text can be used as powerful recombination operators for Evolution Strategies. You can find the paper here.
Furthermore, our second work, Evolution Transformer 🤖, uses supervised pre-training of Transformers to act like Evolution Strategies using Algorithm Distillation of teachers. We explore fine-tuning using meta-evolution and outline a strategy to train the Transformer in a fully self-referential fashion. You can find the paper here.
🧬 DiscoPOP/LLM² Paper Is Out 🦾
Published:
Stoked to share that our Sakana.AI paper on leveraging LLMs to discover better preference optimization algorithms is now available on arXiv 📝! We explore the capabilities of LLMs for automated scientific discovery. This was an outstanding collaboration with Cambridge and Oxford University! LLMs will completely revolutinize the scientific process 🚀
🔖 Paper: here. 💻 Code: here. 🕸 Blog: here. 🐥 Twitter: here.
🌍 Rejax & Meta-Synth-Envs Are Out 🛠
Published:
Super excited to share that our work on fast hardware-accelerated Deep RL algorithms 🚀 and Synthetic Environments 🌎 is finally out!
We implement various DRL algorithms (PPO, DQN, DDPG, SAC, etc.) in pure JAX, which are all nicely packaged into rejax. Furthermore, we leverage meta-evolution (with evosax) to discover synthetic MDPs (more specifically contextual bandits!!!) for fast training of agents that perform well in their real counterpart environments.
This work was led by my fantastic MSc student Jarek Liesen who will soon join FLAIR at the University of Oxford for his PhD. I am extremely grateful for the opportunity to work with such brilliant students!
🤖 Rejax: here. 🌏 Synth-Gymnax: here. 📃 Paper: here. 🐥 Twitter: here.
An AI Scientist 🧑🔬 for everyone!
Published:
🎉 Stoked to share The AI-Scientist 🧑🔬 - our end-to-end approach for conducting research with LLMs including ideation, coding, experiment execution, paper write-up & reviewing. The future of science in the 21st centure is bright❣️
Blog 📰: Link Paper 📜: Link Code 💻: Link Tweet 🕊: Link Talk 🎙: Link
portfolio
publications
RandNLA for Generalized Linear Models with Big Datasets
Published in UPF/UAB Public Online Repository, 2017
Barcelona GSE Masters Thesis which generalizes RandNLA to GLMs.
Recommended citation: Lange, Robert Tjarko. (2017). "Randomized Numerical Linear Algebra for Generalized Linear Models with Big Datasets." UPF/UAB Public Online Repository.
Action Grammars: A Grammar Induction-Based Method for Learning Temporally-Extended Actions
Published in Best (Applied) MAC/MRes/Specialism Project, Sponsored by Winton Capital at Imperial College London, 2018
Imperial College London Masters Thesis which provides a Context-Free Grammar based framework for learning temporal abstractions in Hierarchical Reinforcement Learning.
Recommended citation: Lange, Robert Tjarko. (2018). "Action Grammars: A Grammar Induction-Based Method for Learning Temporally-Extended Actions." Imperial College London - DoC - Best (Applied) MAC/MRes/Specialism Project 2018.
Learning not to learn: Nature versus nurture in silico
Published in -, 2020
We investigate the role of ecological uncertainty, task complexity and lifetime on the qualitative differences between meta-learning adaptation strategies.
Recommended citation: Lange, Robert Tjarko and Sprekeler, Henning. (2020). "Learning not to learn: Nature versus Nurture in Silico." arXiv. Under review..