Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Kabra, Anmol"'
We present a framework for designing scores to summarize performance metrics. Our design has two multi-criteria objectives: (1) improving on scores should improve all performance metrics, and (2) achieving pareto-optimal scores should achieve pareto-
Externí odkaz:
http://arxiv.org/abs/2410.06290
Autor:
Kabra, Anmol, Patel, Kumar Kshitij
We study stochastic optimization in the context of performative shifts, where the data distribution changes in response to the deployed model. We demonstrate that naive retraining can be provably suboptimal even for simple distribution shifts. The is
Externí odkaz:
http://arxiv.org/abs/2408.08499
Autor:
Kabra, Anmol, Elenberg, Ethan R.
Large, general purpose language models have demonstrated impressive performance across many different conversational domains. While multi-domain language models achieve low overall perplexity, their outputs are not guaranteed to stay within the domai
Externí odkaz:
http://arxiv.org/abs/2305.14208
We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the reward is bounded and known. S
Externí odkaz:
http://arxiv.org/abs/2112.14195
Autor:
Kabra, Anmol, Elenberg, Ethan R.
Large, general purpose language models have demonstrated impressive performance across many different conversational domains. While multi-domain language models achieve low overall perplexity, their outputs are not guaranteed to stay within the domai
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0d128379b2281521bb63d6915b1a91fe
http://arxiv.org/abs/2305.14208
http://arxiv.org/abs/2305.14208