5 papers
LatentGym: A Testbed For Cross-Task Experiential Learning With Controllable Latent Structure
Daksh Mittal, Tommaso Castellani, Thomson Yen +7
We envision continually learning agentic systems that become more useful over time: as they encounter sequences of related tasks, they should infer the hidden structure shared acro…
Approximate posterior recalibration
Tiffany Cai, Philip Greengard, Ben Goodrich +1
Bayesian inference is often implemented using approximations, which can yield interval estimates that are too narrow, not fully capturing the uncertainty in the posterior distribut…
Contextual Thompson Sampling via Generation of Missing Data
Kelly W. Zhang, Tiffany Tianhui Cai, Hongseok Namkoong +1
We introduce a framework for Thompson sampling (TS) contextual bandit algorithms, in which the algorithm's ability to quantify uncertainty and make decisions depends on the quality…
Active Exploration via Autoregressive Generation of Missing Data
Tiffany Tianhui Cai, Hongseok Namkoong, Daniel Russo +1
We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model, an area experiencing rap…
C-Learner: Constrained Learning for Causal Inference
Tiffany Tianhui Cai, Yuri Fonseca, Kaiwen Hou +1
Debiasing methods such as augmented inverse propensity weighting (AIPW), and targeted maximum likelihood estimation (TMLE) enjoy asymptotic properties like semiparametric efficienc…