79 citations · 440 across the 39 of their papers we have counts for
12 papers · 1 filter
Towards Understanding How Machines Can Learn Causal Overhypotheses
Eliza Kosoy, David M. Chan, Adrian Liu +7
Recent work in machine learning and cognitive science has suggested that understanding causal information is essential to the development of intelligence. The extensive literature…
Learning Causal Overhypotheses through Exploration in Children and Computational Models
Eliza Kosoy, Adrian Liu, Jasmine Collins +7
Despite recent progress in reinforcement learning (RL), RL algorithms for exploration still remain an active area of research. Existing methods often focus on state-based metrics,…
DCUR: Data Curriculum for Teaching via Samples with Reinforcement Learning
Daniel Seita, Abhinav Gopal, Zhao Mandi +1
Deep reinforcement learning (RL) has shown great empirical successes, but suffers from brittleness and sample inefficiency. A potential remedy is to use a previously-trained policy…
Compressive Visual Representations
Kuang-Huei Lee, Anurag Arnab, Sergio Guadarrama +2
Learning effective visual representations that generalize well without human supervision is a fundamental problem in order to apply Machine Learning to a wide variety of tasks. Rec…
Predictive Information Accelerates Learning in RL
Kuang-Huei Lee, Ian Fischer, Anthony Liu +4
The Predictive Information is the mutual information between the past and the future, I(X_past; X_future). We hypothesize that capturing the predictive information is useful in RL,…
ZPD Teaching Strategies for Deep Reinforcement Learning from Demonstrations
Daniel Seita, David Chan, Roshan Rao +3
Learning from demonstrations is a popular tool for accelerating and reducing the exploration requirements of reinforcement learning. When providing expert demonstrations to human s…
Evaluating Protein Transfer Learning with TAPE
Roshan Rao, Nicholas Bhattacharya, Neil Thomas +5
Protein modeling is an increasingly popular area of machine learning research. Semi-supervised learning has emerged as an important paradigm in protein modeling due to the high cos…
Risk Averse Robust Adversarial Reinforcement Learning
Xinlei Pan, Daniel Seita, Yang Gao +1
Deep reinforcement learning has recently made significant progress in solving computer games and robotic control tasks. A known problem, though, is that policies overfit to the tra…
t-SNE-CUDA: GPU-Accelerated t-SNE and its Applications to Modern Data
David M. Chan, Roshan Rao, Forrest Huang +1
Modern datasets and models are notoriously difficult to explore and analyze due to their inherent high dimensionality and massive numbers of samples. Existing visualization methods…
An Efficient Minibatch Acceptance Test for Metropolis-Hastings
Daniel Seita, Xinlei Pan, Haoyu Chen +1
We present a novel Metropolis-Hastings method for large datasets that uses small expected-size minibatches of data. Previous work on reducing the cost of Metropolis-Hastings tests…
Fast Parallel SAME Gibbs Sampling on General Discrete Bayesian Networks
Daniel Seita, Haoyu Chen, John Canny
A fundamental task in machine learning and related fields is to perform inference on Bayesian networks. Since exact inference takes exponential time in general, a variety of approx…
SAME but Different: Fast and High-Quality Gibbs Parameter Estimation
Huasha Zhao, Biye Jiang, John Canny
Gibbs sampling is a workhorse for Bayesian inference but has several limitations when used for parameter estimation, and is often much slower than non-sampling inference methods. S…