Search Results for author:
Found 37 papers, 16 papers with code
OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training.
Autoformalization with Large Language Models
Autoformalization is the process of automatically translating from natural language mathematics to formal specifications and proofs.
Ranked #1 on
Automated Theorem Proving
on miniF2F-test
(using extra training data)
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
Thor increases a language model's success rate on the PISA dataset from $39\%$ to $57\%$, while solving $8. 2\%$ of problems neither language models nor automated theorem provers are able to solve on their own.
Ranked #2 on
Automated Theorem Proving
on miniF2F-test
STaR: Bootstrapping Reasoning With Reasoning
We show that STaR significantly improves performance on multiple datasets compared to a model fine-tuned to directly predict final answers, and performs comparably to fine-tuning a 30$\times$ larger state-of-the-art language model on CommensenseQA.
Ranked #9 on
Common Sense Reasoning
on CommonsenseQA
Memorizing Transformers
Language models typically need to be trained or finetuned in order to acquire new knowledge, which involves updating their weights.
Block-Recurrent Transformers
It is merely a transformer layer: it uses self-attention and cross-attention to efficiently compute a recurrent function over a large set of state vectors and tokens.
Hierarchical Transformers Are More Efficient Language Models
Transformer models yield impressive results on many NLP and sequence modeling tasks.
Ranked #4 on
Image Generation
on ImageNet 32x32
(bpd metric)
Invariant Causal Representation Learning for Out-of-Distribution Generalization
Extensive experiments on both synthetic and real-world datasets show that our approach outperforms a variety of baseline methods.
REFACTOR: Learning to Extract Theorems from Proofs
With newly extracted theorems, we show that the existing proofs in the MetaMath database can be refactored.
Learning to Give Checkable Answers with Prover-Verifier Games
We develop instantiations of the PVG for two algorithmic tasks, and show that in practice, the verifier learns a robust decision rule that is able to receive useful and reliable information from an untrusted prover.
Subgoal Search For Complex Reasoning Tasks
In this paper, we implement kSubS using a transformer-based subgoal module coupled with the classical best-first search framework.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Nonlinear Invariant Risk Minimization: A Causal Approach
Finally, in the discussion, we further explore the aforementioned assumption and propose a more general hypothesis, called the Agnostic Hypothesis: there exist a set of hidden causal factors affecting both inputs and outcomes.
Proof Artifact Co-training for Theorem Proving with Language Models
Labeled data for imitation learning of theorem proving in large libraries of formalized mathematics is scarce as such libraries require years of concentrated effort by human specialists to be built.
LIME: Learning Inductive Bias for Primitives of Mathematical Reasoning
While designing inductive bias in neural architectures has been widely studied, we hypothesize that transformer networks are flexible enough to learn inductive bias from suitable generic tasks.
Invariant Causal Representation Learning
As an alternative, we propose Invariant Causal Representation Learning (ICRL), a learning paradigm that enables out-of-distribution generalization in the nonlinear setting (i. e., nonlinear representations and nonlinear classifiers).
The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning
In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM).
Learning Branching Heuristics for Propositional Model Counting
Propositional model counting or #SAT is the problem of computing the number of satisfying assignments of a Boolean formula and many discrete probabilistic inference problems can be translated into a model counting problem to be solved by #SAT solvers.
INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
In learning-assisted theorem proving, one of the most critical challenges is to generalize to theorems unlike those seen at training time.
IsarStep: a Benchmark for High-level Mathematical Reasoning
In this paper, we present a benchmark for high-level mathematical reasoning and study the reasoning capabilities of neural sequence-to-sequence models.
A Non-asymptotic comparison of SVRG and SGD: tradeoffs between compute and speed
In this paper, we present a non-asymptotic analysis of SVRG under a noisy least squares regression problem.
Options as responses: Grounding behavioural hierarchies in multi-agent RL
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training.
ACTRCE: Augmenting Experience via Teacher’s Advice
Sparse reward is one of the most challenging problems in reinforcement learning (RL).
Concurrent Meta Reinforcement Learning
In this multi-agent setting, a set of parallel agents are executed in the same environment and each of these "rollout" agents are given the means to communicate with each other.
Ranked #1 on
Meta Reinforcement Learning
on 10-Monty-Hall
ACTRCE: Augmenting Experience via Teacher's Advice For Multi-Goal Reinforcement Learning
We first analyze the differences among goal representation, and show that ACTRCE can efficiently solve difficult reinforcement learning problems in challenging 3D navigation tasks, whereas HER with non-language goal representation failed to learn.
The Importance of Sampling inMeta-Reinforcement Learning
Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning.
Understanding Short-Horizon Bias in Stochastic Meta-Optimization
Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training.
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
We consider the problem of exploration in meta reinforcement learning.
An Empirical Analysis of Proximal Policy Optimization with Kronecker-factored Natural Gradients
In this technical report, we consider an approach that combines the PPO objective and K-FAC natural gradient optimization, for which we call PPOKFAC.
Backpropagation through the Void: Optimizing control variates for black-box gradient estimation
Gradient-based optimization is the foundation of deep learning and reinforcement learning.
Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation
In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature.
Sticking the Landing: Simple, Lower-Variance Gradient Estimators for Variational Inference
We propose a simple and general variant of the standard reparameterized gradient estimator for the variational evidence lower bound.
On the Quantitative Analysis of Decoder-Based Generative Models
The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities.
On Multiplicative Integration with Recurrent Neural Networks
We introduce a general and simple structural design called Multiplicative Integration (MI) to improve recurrent neural networks (RNNs).
Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations
We investigate the parameter-space geometry of recurrent neural networks (RNNs), and develop an adaptation of path-SGD optimization method, attuned to this geometry, that can learn plain RNNs with ReLU activations.
Architectural Complexity Measures of Recurrent Neural Networks
In this paper, we systematically analyze the connecting architectures of recurrent neural networks (RNNs).
Ranked #21 on
Language Modelling
on Text8
STDP as presynaptic activity times rate of change of postsynaptic activity
We introduce a weight update formula that is expressed only in terms of firing rates and their derivatives and that results in changes consistent with those associated with spike-timing dependent plasticity (STDP) rules and biological observations, even though the explicit timing of spikes is not needed.
