Publications

Handling Delay in Reinforcement Learning Caused by Parallel Computations of Neurons
Ivan Anokhin
Rishav
Stephen Chung
Irina Rish
Samira Ebrahimi Kahou
Biological neural networks operate in parallel, a feature that sets them apart from artificial neural networks and can significantly enhance… (voir plus) inference speed. However, this parallelism introduces challenges: when each neuron operates asynchronously with a fixed execution time, an
2024-06-19
ICML.cc/2024/Workshop/ARLET (poster)
openreview.net
openreview.net
Realtime Reinforcement Learning: Towards Rapid Asynchronous Deployment of Large Models
Matthew D Riemer
Gopeshh Subbaraj
Glen Berseth
Irina Rish
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectivel… (voir plus)y minimize long-term regret. However, recent advances in machine learning involve larger neural networks with longer inference times, raising questions about their applicability in realtime systems where reaction time is crucial. We present an analysis of lower bounds on regret in realtime environments to show that minimizing long-term regret is generally impossible within the typical sequential interaction and learning paradigm, but often becomes possible when sufficient asynchronous compute is available. We propose novel algorithms for staggering asynchronous inference processes to ensure that actions are taken at consistent time intervals, and demonstrate that use of models with high action inference times is only constrained by the environment's effective stochasticity over the inference horizon, and not by action frequency. Our analysis shows that the number of inference processes needed scales linearly with increasing inference times while enabling use of models that are multiple orders of magnitude larger than existing approaches when learning from a realtime simulation of Game Boy games such as Pokemon and Tetris.
2024-06-19
ICML.cc/2024/Workshop/ARLET (poster)
openreview.net
openreview.net
Many-Shot In-Context Learning
Rishabh Agarwal
Avi Singh
Lei M Zhang
Bernd Bohnet
Luis Rosias
Stephanie C.Y. Chan
Ankesh Anand
Zaheer Abbas
Biao Zhang
Azade Nova
John D. Co-Reyes
Eric Chu
Feryal M. P. Behbahani
Aleksandra Faust
Hugo Larochelle
Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, w… (voir plus)ithout any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples -- the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated examples. To mitigate this limitation, we explore two new settings: Reinforced and Unsupervised ICL. Reinforced ICL uses model-generated chain-of-thought rationales in place of human examples. Unsupervised ICL removes rationales from the prompt altogether, and prompts the model only with domain-specific questions. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. Finally, we demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases and can learn high-dimensional functions with numerical inputs. Our analysis also reveals the limitations of next-token prediction loss as an indicator of downstream ICL performance.
2024-06-18
ICML.cc/2024/Workshop/ICL (poster)
doi.org
openreview.net
Many-Shot In-Context Learning
Rishabh Agarwal
Avi Singh
Lei M Zhang
Bernd Bohnet
Luis Rosias
Stephanie C.Y. Chan
Ankesh Anand
Zaheer Abbas
Biao Zhang
Azade Nova
John D Co-Reyes
Eric Chu
Feryal Behbahani
Aleksandra Faust
Hugo Larochelle
Large language models (LLMs) excel at few-shot in-context learning (ICL) -- learning from a few examples provided in context at inference, w… (voir plus)ithout any weight updates. Newly expanded context windows allow us to investigate ICL with hundreds or thousands of examples – the many-shot regime. Going from few-shot to many-shot, we observe significant performance gains across a wide variety of generative and discriminative tasks. While promising, many-shot ICL can be bottlenecked by the available amount of human-generated outputs. To mitigate this limitation, we explore two new settings: (1) "Reinforced ICL" that uses model-generated chain-of-thought rationales in place of human rationales, and (2) "Unsupervised ICL" where we remove rationales from the prompt altogether, and prompts the model only with domain-specific inputs. We find that both Reinforced and Unsupervised ICL can be quite effective in the many-shot regime, particularly on complex reasoning tasks. We demonstrate that, unlike few-shot learning, many-shot learning is effective at overriding pretraining biases, can learn high-dimensional functions with numerical inputs, and performs comparably to supervised fine-tuning. Finally, we reveal the limitations of next-token prediction loss as an indicator of downstream ICL performance.
2024-06-18
ICML.cc/2024/Workshop/ICL (poster)
doi.org
openreview.net
More Efficient Randomized Exploration for Reinforcement Learning via Approximate Sampling
Haque Ishfaq
Yixin Tan
Yu Yang
Qingfeng Lan
Jianfeng Lu
A. Rupam Mahmood
Doina Precup
Pan Xu
2024-06-18
ArXiv (prépublication)
doi.org
arxiv.org
Performative Prediction on Games and Mechanism Design
António Góis
Mehrnaz Mofakhami
Fernando P. Santos
Simon Lacoste-Julien
Gauthier Gidel
2024-06-18
ICML.cc/2024/Workshop/Agentic_Markets (poster)
openreview.net
openreview.net
Probabilistic Temporal Prediction of Continuous Disease Trajectories and Treatment Effects Using Neural SDEs
Joshua D. Durso-Finley
Berardino Barile
Jean-Pierre R. Falet
Douglas Arnold
Nick Pawlowski
Tal Arbel
Personalized medicine based on medical images, including predicting future individualized clinical disease progression and treatment respons… (voir plus)e, would have an enormous impact on healthcare and drug development, particularly for diseases (e.g. multiple sclerosis (MS)) with long term, complex, heterogeneous evolutions and no cure. In this work, we present the first stochastic causal temporal framework to model the continuous temporal evolution of disease progression via Neural Stochastic Differential Equations (NSDE). The proposed causal inference model takes as input the patient's high dimensional images (MRI) and tabular data, and predicts both factual and counterfactual progression trajectories on different treatments in latent space. The NSDE permits the estimation of high-confidence personalized trajectories and treatment effects. Extensive experiments were performed on a large, multi-centre, proprietary dataset of patient 3D MRI and clinical data acquired during several randomized clinical trials for MS treatments. Our results present the first successful uncertainty-based causal Deep Learning (DL) model to: (a) accurately predict future patient MS disability evolution (e.g. EDSS) and treatment effects leveraging baseline MRI, and (b) permit the discovery of subgroups of patients for which the model has high confidence in their response to treatment even in clinical trials which did not reach their clinical endpoints.
2024-06-18
ArXiv (prépublication)
doi.org
arxiv.org
Scalable Approaches for a Theory of Many Minds
Maximilian Puelma Touzel
Amin Memarian
Matthew D Riemer
Andrei Mircea
Andrew Robert Williams
Elin Ahlstrand
Lucas Lehnert
Rupali Bhati
Guillaume Dumas
Irina Rish
A major challenge as we move towards building agents for real-world problems, which could involve a massive number of human and/or machine a… (voir plus)gents, is that we must learn to reason about the behavior of these many other agents. In this paper, we consider the problem of scaling a predictive Theory of Mind (ToM) model to a very large number of interacting agents with a fixed computational budget. Motivated by the limited diversity of agent types, existing approaches to scalable TOM learn versatile single-agent representations for quickly adapting to new agents encountered sequentially. We consider the more general setting that many agents are observed in parallel and formulate the corresponding Theory of Many Minds (ToMM) problem of estimating the joint policy. We frame the scaling behavior of solutions in terms of parameter sharing schemes and in particular propose two parameter-free architectural features that endow models with the ability to exploit action correlations: encoding a multi-agent context, and decoding through an abstracted joint action space. The increased predictive capabilities that have come with foundation models have made it easier to imagine the possibility of using these models to make simulations that imitate the behavior of many agents within complex real-world systems. Being able to perform these simulations in a general-purpose way would not only help make more capable agents, it also would be a very useful capability for applications in social science, political science, and economics.
2024-06-18
ICML.cc/2024/Workshop/Agentic_Markets (poster)
openreview.net
openreview.net
Assessing the Viability of Generative Modeling in Simulated Astronomical Observations
Patrick Janulewicz
Laurence Perreault-Levasseur
Tracy Webb
In this paper, we use methods for assessing the quality of generative models and apply them to a problem from the physical sciences. We turn… (voir plus) our attention to astrophysics, where cosmological simulations are often used to create mock observations that mimic telescope images. These simulations and their mock observations are often slow and challenging to generate, inspiring some to use generative modeling to enhance the amount of data available to study. In this work, we add realism to simulated images of galaxy clusters and use probability mass estimation to assess their fidelity compared to reality. We find that the simulations are biased compared to real observations and suggest that researchers applying generative modeling to these systems should proceed with caution.
2024-06-17
ICML.cc/2024/Workshop/SPIGM (poster)
openreview.net
openreview.net
Augmenting Evolutionary Models with Structure-based Retrieval
Yining Huang
Zuobai Zhang
Jian Tang
Debora Susan Marks
Pascal Notin
2024-06-17
ICML.cc/2024/Workshop/ML4LMS (poster)
openreview.net
openreview.net
Bias-inducing geometries: exactly solvable data model with fairness implications
Stefano Sarao Mannelli
Federica Gerace
Negar Rostamzadeh
Luca Saglietti
Machine learning (ML) may be oblivious to human bias but it is not immune to its perpetuation. Marginalisation and iniquitous group represen… (voir plus)tation are often traceable in the very data used for training, and may be reflected or even enhanced by the learning models. In this abstract, we aim to clarify the role played by data geometry in the emergence of ML bias. We introduce an exactly solvable high-dimensional model of data imbalance, where parametric control over the many bias-inducing factors allows for an extensive exploration of the bias inheritance mechanism. Through the tools of statistical physics, we analytically characterise the typical properties of learning models trained in this synthetic framework and obtain exact predictions for the observables that are commonly employed for fairness assessment. Simplifying the nature of the problem to its minimal components, we can retrace and unpack typical unfairness behaviour observed on real-world datasets
2024-06-17
ICML.cc/2024/Workshop/GRaM (publié)
openreview.net
openreview.net
Demystifying amortized causal discovery with transformers
Francesco Montagna
Max Cairney-Leeming
Dhanya Sridhar
Francesco Locatello
Supervised learning approaches for causal discovery from observational data often achieve competitive performance despite seemingly avoiding… (voir plus) explicit assumptions that traditional methods make for identifiability. In this work, we investigate CSIvA \citep{ke2023learning}, a transformer-based model promising to train on synthetic data and transfer to real data. First, we bridge the gap with existing identifiability theory and show that constraints on the training data distribution implicitly define a prior on the test observations. Consistent with classical approaches, good performance is achieved when we have a good prior on the test data, and the underlying model is identifiable. At the same time, we find new trade-offs. Training on datasets generated from different classes of causal models, unambiguously identifiable in isolation, improves the test generalization. Performance is still guaranteed, as the ambiguous cases resulting from the mixture of identifiable causal models are unlikely to occur (which we formally prove). Overall, our study finds that amortized causal discovery still needs to obey identifiability theory, but it also differs from classical methods in how the assumptions are formulated, trading more reliance on assumptions on the noise type for fewer hypotheses on the mechanisms.
2024-06-17
ICML.cc/2024/Workshop/SPIGM (poster)
openreview.net
openreview.net