Search Results for author: Peter Battaglia

Found 37 papers, 14 papers with code

Pre-training via Denoising for Molecular Property Prediction

no code implementations31 May 2022 Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter Battaglia, Razvan Pascanu, Jonathan Godwin

Many important problems involving molecular property prediction from 3D structures have limited data, posing a generalization challenge for neural networks.

Denoising Molecular Property Prediction

Rediscovering orbital mechanics with machine learning

no code implementations4 Feb 2022 Pablo Lemos, Niall Jeffrey, Miles Cranmer, Shirley Ho, Peter Battaglia

We then use symbolic regression to discover an analytical expression for the force law implicitly learned by the neural network, which our results showed is equivalent to Newton's law of gravitation.

Symbolic Regression

Physical Design using Differentiable Learned Simulators

no code implementations1 Feb 2022 Kelsey R. Allen, Tatiana Lopez-Guevara, Kimberly Stachenfeld, Alvaro Sanchez-Gonzalez, Peter Battaglia, Jessica Hamrick, Tobias Pfaff

In our fluid manipulation tasks, the resulting designs outperformed those found by sampling-based optimization techniques.

Learned Coarse Models for Efficient Turbulence Simulation

no code implementations31 Dec 2021 Kimberly Stachenfeld, Drummond B. Fielding, Dmitrii Kochkov, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Can Cui, Shirley Ho, Peter Battaglia, Alvaro Sanchez-Gonzalez

We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the comparably low resolutions across various scientifically relevant metrics.

Constraint-based graph network simulator

no code implementations16 Dec 2021 Yulia Rubanova, Alvaro Sanchez-Gonzalez, Tobias Pfaff, Peter Battaglia

We can improve the simulation accuracy on a larger system by applying more solver iterations at test time.

Physical Simulations

Learning ground states of quantum Hamiltonians with graph networks

no code implementations12 Oct 2021 Dmitrii Kochkov, Tobias Pfaff, Alvaro Sanchez-Gonzalez, Peter Battaglia, Bryan K. Clark

In this work we use graph neural networks to define a structured variational manifold and optimize its parameters to find high quality approximations of the lowest energy solutions on a diverse set of Heisenberg Hamiltonians.

Learned Simulators for Turbulence

no code implementations ICLR 2022 Kim Stachenfeld, Drummond Buschman Fielding, Dmitrii Kochkov, Miles Cranmer, Tobias Pfaff, Jonathan Godwin, Can Cui, Shirley Ho, Peter Battaglia, Alvaro Sanchez-Gonzalez

We show that our proposed model can simulate turbulent dynamics more accurately than classical numerical solvers at the same low resolutions across various scientifically relevant metrics.

Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond

no code implementations ICLR 2022 Jonathan Godwin, Michael Schaarschmidt, Alexander L Gaunt, Alvaro Sanchez-Gonzalez, Yulia Rubanova, Petar Veličković, James Kirkpatrick, Peter Battaglia

We introduce “Noisy Nodes”, a very simple technique for improved training of GNNs, in which we corrupt the input graph with noise, and add a noise correcting node-level loss.

Molecular Property Prediction

A Bayesian neural network predicts the dissolution of compact planetary systems

2 code implementations11 Jan 2021 Miles Cranmer, Daniel Tamayo, Hanno Rein, Peter Battaglia, Samuel Hadden, Philip J. Armitage, Shirley Ho, David N. Spergel

Our model, trained directly from short N-body time series of raw orbital elements, is more than two orders of magnitude more accurate at predicting instability times than analytical estimators, while also reducing the bias of existing machine learning algorithms by nearly a factor of three.

Time Series

Graph Networks with Spectral Message Passing

no code implementations31 Dec 2020 Kimberly Stachenfeld, Jonathan Godwin, Peter Battaglia

Our model projects vertices of the spatial graph onto the Laplacian eigenvectors, which are each represented as vertices in a fully connected "spectral graph", and then applies learned message passing to them.

Molecular Property Prediction Relational Reasoning

Continuous Latent Search for Combinatorial Optimization

no code implementations NeurIPS Workshop LMCA 2020 Sergey Bartunov, Vinod Nair, Peter Battaglia, Tim Lillicrap

Combinatorial optimization problems are notoriously hard because they often require enumeration of the exponentially large solution space.

Combinatorial Optimization

Graph Neural Networks in Particle Physics

no code implementations27 Jul 2020 Jonathan Shlomi, Peter Battaglia, Jean-Roch Vlimant

Particle physics is a branch of science aiming at discovering the fundamental laws of matter and forces.

High Energy Physics - Experiment High Energy Physics - Phenomenology

Predicting the long-term stability of compact multiplanet systems

1 code implementation13 Jul 2020 Daniel Tamayo, Miles Cranmer, Samuel Hadden, Hanno Rein, Peter Battaglia, Alysa Obertas, Philip J. Armitage, Shirley Ho, David Spergel, Christian Gilbertson, Naireen Hussain, Ari Silburt, Daniel Jontof-Hutter, Kristen Menou

Our Stability of Planetary Orbital Configurations Klassifier (SPOCK) predicts stability using physically motivated summary statistics measured in integrations of the first $10^4$ orbits, thus achieving speed-ups of up to $10^5$ over full simulations.

Earth and Planetary Astrophysics

Discovering Symbolic Models from Deep Learning with Inductive Biases

3 code implementations NeurIPS 2020 Miles Cranmer, Alvaro Sanchez-Gonzalez, Peter Battaglia, Rui Xu, Kyle Cranmer, David Spergel, Shirley Ho

The technique works as follows: we first encourage sparse latent representations when we train a GNN in a supervised setting, then we apply symbolic regression to components of the learned model to extract explicit physical relations.

Symbolic Regression

Hamiltonian Graph Networks with ODE Integrators

no code implementations27 Sep 2019 Alvaro Sanchez-Gonzalez, Victor Bapst, Kyle Cranmer, Peter Battaglia

We introduce an approach for imposing physically informed inductive biases in learned simulation models.

AlignNet: Self-supervised Alignment Module

no code implementations25 Sep 2019 Antonia Creswell, Luis Piloto, David Barrett, Kyriacos Nikiforou, David Raposo, Marta Garnelo, Peter Battaglia, Murray Shanahan

The natural world consists of objects that we perceive as persistent in space and time, even though these objects appear, disappear and reappear in our field of view as we move.

Question Answering

Learning Symbolic Physics with Graph Networks

no code implementations12 Sep 2019 Miles D. Cranmer, Rui Xu, Peter Battaglia, Shirley Ho

We introduce an approach for imposing physically motivated inductive biases on graph networks to learn interpretable representations and improved zero-shot generalization.

Inductive Bias Symbolic Regression

Deep reinforcement learning with relational inductive biases

no code implementations ICLR 2019 Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia

We introduce an approach for augmenting model-free deep reinforcement learning agents with a mechanism for relational reasoning over structured representations, which improves performance, learning efficiency, generalization, and interpretability.

reinforcement-learning Relational Reasoning +2

CompILE: Compositional Imitation Learning and Execution

3 code implementations4 Dec 2018 Thomas Kipf, Yujia Li, Hanjun Dai, Vinicius Zambaldi, Alvaro Sanchez-Gonzalez, Edward Grefenstette, Pushmeet Kohli, Peter Battaglia

We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data.

Continuous Control Imitation Learning

Modeling human intuitions about liquid flow with particle-based simulation

no code implementations5 Sep 2018 Christopher J. Bates, Ilker Yildirim, Joshua B. Tenenbaum, Peter Battaglia

Humans can easily describe, imagine, and, crucially, predict a wide variety of behaviors of liquids--splashing, squirting, gushing, sloshing, soaking, dripping, draining, trickling, pooling, and pouring--despite tremendous variability in their material and dynamical properties.

Scene Understanding

Learning Visual Question Answering by Bootstrapping Hard Attention

no code implementations ECCV 2018 Mateusz Malinowski, Carl Doersch, Adam Santoro, Peter Battaglia

Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all sensory inputs.

Hard Attention Question Answering +1

Relational Deep Reinforcement Learning

7 code implementations5 Jun 2018 Vinicius Zambaldi, David Raposo, Adam Santoro, Victor Bapst, Yujia Li, Igor Babuschkin, Karl Tuyls, David Reichert, Timothy Lillicrap, Edward Lockhart, Murray Shanahan, Victoria Langston, Razvan Pascanu, Matthew Botvinick, Oriol Vinyals, Peter Battaglia

We introduce an approach for deep reinforcement learning (RL) that improves upon the efficiency, generalization capacity, and interpretability of conventional approaches through structured perception and relational reasoning.

reinforcement-learning Relational Reasoning +2

Graph networks as learnable physics engines for inference and control

1 code implementation ICML 2018 Alvaro Sanchez-Gonzalez, Nicolas Heess, Jost Tobias Springenberg, Josh Merel, Martin Riedmiller, Raia Hadsell, Peter Battaglia

Understanding and interacting with everyday physical scenes requires rich knowledge about the structure of the world, represented either implicitly in a value or policy function, or explicitly in a transition model.

Inductive Bias

Hyperbolic Attention Networks

no code implementations ICLR 2019 Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas

We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.

Machine Translation Question Answering +2

Learning Deep Generative Models of Graphs

no code implementations ICLR 2018 Yujia Li, Oriol Vinyals, Chris Dyer, Razvan Pascanu, Peter Battaglia

Graphs are fundamental data structures which concisely capture the relational structure in many important real-world domains, such as knowledge graphs, physical and social interactions, language, and chemistry.

Graph Generation Knowledge Graphs

Visual Interaction Networks: Learning a Physics Simulator from Video

no code implementations NeurIPS 2017 Nicholas Watters, Daniel Zoran, Theophane Weber, Peter Battaglia, Razvan Pascanu, Andrea Tacchetti

We introduce the Visual Interaction Network, a general-purpose model for learning the dynamics of a physical system from raw visual observations.

Decision Making

Learning model-based planning from scratch

1 code implementation19 Jul 2017 Razvan Pascanu, Yujia Li, Oriol Vinyals, Nicolas Heess, Lars Buesing, Sebastien Racanière, David Reichert, Théophane Weber, Daan Wierstra, Peter Battaglia

Here we introduce the "Imagination-based Planner", the first model-based, sequential decision-making agent that can learn to construct, evaluate, and execute plans.

Continuous Control Decision Making

Visual Interaction Networks

2 code implementations5 Jun 2017 Nicholas Watters, Andrea Tacchetti, Theophane Weber, Razvan Pascanu, Peter Battaglia, Daniel Zoran

We found that from just six input video frames the Visual Interaction Network can generate accurate future trajectories of hundreds of time steps on a wide range of physical systems.

Decision Making

Learning to Perform Physics Experiments via Deep Reinforcement Learning

no code implementations6 Nov 2016 Misha Denil, Pulkit Agrawal, Tejas D. Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas

When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way.

Natural Language Processing reinforcement-learning

Cannot find the paper you are looking for? You can Submit a new open access paper.