238 citations · 242 across the 17 of their papers we have counts for
4 papers · 1 filter
Faster Policy Learning with Continuous-Time Gradients
Samuel Ainsworth, Kendall Lowrey, John Thickstun +2
We study the estimation of policy gradients for continuous-time systems with known dynamics. By reframing policy learning in continuous-time, we show that it is possible construct…
Rethinking Evaluation Methodology for Audio-to-Score Alignment
John Thickstun, Jennifer Brennan, Harsh Verma
This paper offers a precise, formal definition of an audio-to-score alignment. While the concept of an alignment is intuitively grasped, this precision affords us new insight into…
An Information Bottleneck Approach for Controlling Conciseness in Rationale Extraction
Bhargavi Paranjape, Mandar Joshi, John Thickstun +2
Decisions of complex language understanding models can be rationalized by limiting their inputs to a relevant subsequence of the original text. A rationale should be as concise as…
Source Separation with Deep Generative Priors
Vivek Jayaram, John Thickstun
Despite substantial progress in signal source separation, results for richly structured data continue to contain perceptible artifacts. In contrast, recent deep generative models c…