503 citations · 1.3k across the 34 of their papers we have counts for
10 papers · 1 filter
Unifying Grokking and Double Descent
Xander Davies, Lauro Langosco, David Krueger
A principled understanding of generalization in deep learning may require unifying disparate observations under a single conceptual framework. Previous work has studied \emph{grokk…
Leave Graphs Alone: Addressing Over-Squashing without Rewiring
Domenico Tortorella, Alessio Micheli
Recent works have investigated the role of graph bottlenecks in preventing long-range information propagation in message-passing graph neural networks, causing the so-called `over-…
Neural Payoff Machines: Predicting Fair and Stable Payoff Allocations Among Team Members
Daphne Cornelisse, Thomas Rood, Mateusz Malinowski +2
In many multi-agent settings, participants can form teams to achieve collective outcomes that may far surpass their individual capabilities. Measuring the relative contributions of…
Measuring CLEVRness: Blackbox testing of Visual Reasoning Models
Spyridon Mouselinos, Henryk Michalewski, Mateusz Malinowski
How can we measure the reasoning capabilities of intelligence systems? Visual question answering provides a convenient framework for testing the model's abilities by interrogating…
General-purpose, long-context autoregressive modeling with Perceiver AR
Curtis Hawthorne, Andrew Jaegle, Cătălina Cangea +12
Real-world data is high-dimensional: a book, image, or musical performance can easily contain hundreds of thousands of elements even after compression. However, the most commonly u…
IReEn: Reverse-Engineering of Black-Box Functions via Iterative Neural Program Synthesis
Hossein Hajipour, Mateusz Malinowski, Mario Fritz
In this work, we investigate the problem of revealing the functionality of a black-box agent. Notably, we are interested in the interpretable and formal description of the behavior…
Learning dynamic polynomial proofs
Alhussein Fawzi, Mateusz Malinowski, Hamza Fawzi +1
Polynomial inequalities lie at the heart of many mathematical disciplines. In this paper, we consider the fundamental computational task of automatically searching for proofs of po…
Generating Diverse Programs with Instruction Conditioned Reinforced Adversarial Learning
Aishwarya Agrawal, Mateusz Malinowski, Felix Hill +3
Advances in Deep Reinforcement Learning have led to agents that perform well across a variety of sensory-motor domains. In this work, we study the setting in which an agent must le…
Playing the Game of Universal Adversarial Perturbations
Julien Perolat, Mateusz Malinowski, Bilal Piot +1
We study the problem of learning classifiers robust to universal adversarial perturbations. While prior work approaches this problem via robust optimization, adversarial training,…
Relational inductive biases, deep learning, and graph networks
Peter W. Battaglia, Jessica B. Hamrick, Victor Bapst +24
Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, i…