22 citations · 128 across the 29 of their papers we have counts for
18 papers · 1 filter
Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning
Yash Jhaveri, Harley Wiltzer, Patrick Shafto +2
In the pursuit of finding an optimal policy, reinforcement learning (RL) methods generally ignore the properties of learned policies apart from their expected return. Thus, even wh…
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
Harley Wiltzer, Marc G. Bellemare, David Meger +2
When decisions are made at high frequency, traditional reinforcement learning (RL) methods struggle to accurately estimate action values. In turn, their performance is inconsistent…
Structured Evaluation of Synthetic Tabular Data
Scott Cheng-Hsin Yang, Baxter Eaves, Michael Schmidt +2
Tabular data is common yet typically incomplete, small in volume, and access-restricted due to privacy concerns. Synthetic data generation offers potential solutions. Many metrics…
Evolution of beliefs in social networks
Pushpi Paranamana, Pei Wang, Patrick Shafto
Evolution of beliefs of a society are a product of interactions between people (horizontal transmission) in the society over generations (vertical transmission). Researchers have s…
On Connecting Deep Trigonometric Networks with Deep Gaussian Processes: Covariance, Expressivity, and Neural Tangent Kernel
Chi-Ken Lu, Patrick Shafto
Deep Gaussian Process (DGP) as a model prior in Bayesian learning intuitively exploits the expressive power in function composition. DGPs also offer diverse modeling capabilities,…
Conditional Deep Gaussian Processes: empirical Bayes hyperdata learning
Chi-Ken Lu, Patrick Shafto
It is desirable to combine the expressive power of deep learning with Gaussian Process (GP) in one expressive Bayesian learning model. Deep kernel learning showed success in adopti…
Explainable AI for medical imaging: Explaining pneumothorax diagnoses with Bayesian Teaching
Tomas Folke, Scott Cheng-Hsin Yang, Sean Anderson +1
Limited expert time is a key bottleneck in medical imaging. Due to advances in image classification, AI can now serve as decision-support for medical experts, with the potential fo…
Distributionally-Constrained Policy Optimization via Unbalanced Optimal Transport
Arash Givchi, Pei Wang, Junqi Wang +1
We consider constrained policy optimization in Reinforcement Learning, where the constraints are in form of marginals on state visitations and global action executions. Given these…
Sequential Cooperative Bayesian Inference
Junqi Wang, Pei Wang, Patrick Shafto
Cooperation is often implicitly assumed when learning from other agents. Cooperation implies that the agent selecting the data, and the agent learning from the data, have the same…
Conditional Deep Gaussian Processes: multi-fidelity kernel learning
Chi-Ken Lu, Patrick Shafto
Deep Gaussian Processes (DGPs) were proposed as an expressive Bayesian model capable of a mathematically grounded estimation of uncertainty. The expressivity of DPGs results from n…
Learning a manifold from a teacher's demonstrations
Pei Wang, Arash Givchi, Patrick Shafto
We consider the problem of learning a manifold from a teacher's demonstration. Extending existing approaches of learning from randomly sampled data points, we consider contexts whe…
A mathematical theory of cooperative communication
Pei Wang, Junqi Wang, Pushpi Paranamana +1
Cooperative communication plays a central role in theories of human cognition, language, development, culture, and human-robot interaction. Prior models of cooperative communicatio…
Interpretable deep Gaussian processes with moments
Chi-Ken Lu, Scott Cheng-Hsin Yang, Xiaoran Hao +1
Deep Gaussian Processes (DGPs) combine the expressiveness of Deep Neural Networks (DNNs) with quantified uncertainty of Gaussian Processes (GPs). Expressive power and intractable i…
Generalizing the theory of cooperative inference
Pei Wang, Pushpi Paranamana, Patrick Shafto
Cooperation information sharing is important to theories of human learning and has potential implications for machine learning. Prior work derived conditions for achieving optimal…
Optimal Cooperative Inference
Scott Cheng-Hsin Yang, Yue Yu, Arash Givchi +3
Cooperative transmission of data fosters rapid accumulation of knowledge by efficiently combining experiences across learners. Although well studied in human learning and increasin…
Human-Algorithm Interaction Biases in the Big Data Cycle: A Markov Chain Iterated Learning Framework
Olfa Nasraoui, Patrick Shafto
Early supervised machine learning algorithms have relied on reliable expert labels to build predictive models. However, the gates of data generation have recently been opened to a…
Infant directed speech is consistent with teaching
Baxter S. Eaves, Naomi H. Feldman, Thomas L. Griffiths +1
Infant-directed speech (IDS) has distinctive properties that differ from adult-directed speech (ADS). Why it has these properties -- and whether they are intended to facilitate lan…
Toward a general, scaleable framework for Bayesian teaching with applications to topic models
Baxter S. Eaves, Patrick Shafto
Machines, not humans, are the world's dominant knowledge accumulators but humans remain the dominant decision makers. Interpreting and disseminating the knowledge accumulated by ma…