Zobrazeno 1 - 10
of 23 042
pro vyhledávání: '"Lalitha ."'
Autor:
Rameshwar, V. Arvind, Lalitha, V.
In this paper, we revisit the Recursive Projection-Aggregation (RPA) decoder, of Ye and Abbe (2020), for Reed-Muller (RM) codes. Our main contribution is an explicit upper bound on the probability of incorrect decoding, using the RPA decoder, over a
Externí odkaz:
http://arxiv.org/abs/2412.08129
Autor:
Mukherjee, Subhojyoti, Lalitha, Anusha, Sengupta, Sailik, Deshmukh, Aniket, Kveton, Branislav
Multi-objective alignment from human feedback (MOAHF) in large language models (LLMs) is a challenging problem as human preferences are complex, multifaceted, and often conflicting. Recent works on MOAHF considered a-priori multi-objective optimizati
Externí odkaz:
http://arxiv.org/abs/2412.05469
This paper focuses on solving a stochastic variational inequality (SVI) problem under relaxed smoothness assumption for a class of structured non-monotone operators. The SVI problem has attracted significant interest in the machine learning community
Externí odkaz:
http://arxiv.org/abs/2410.12334
We study gradient methods for solving an optimization problem with an $(L_0, L_1)$-smooth objective function. This problem class generalizes that of Lipschitz-smooth problems and has gained interest recently, as it captures a broader range of machine
Externí odkaz:
http://arxiv.org/abs/2410.10800
Autor:
Sairam, Lalitha, Baycroft, Thomas A., Boisse, Isabelle, Heidari, Neda, Santerne, Alexandre, Triaud, Amaury H. M. J., Coleman, Gavin A. L., Davis, Yasmin T., Deleuil, Magali, Hébrard, Guillaume, Martin, David V., Maxted, Pierre F. L., Nelson, Richard P., Sebastian, Daniel, Scutt, Owen J., Standing, Matthew R.
Circumbinary planets - planets that orbit both stars in a binary system - offer the opportunity to study planet formation and orbital migration in a different environment compare to single stars. However, despite the fact that > 90% of binary systems
Externí odkaz:
http://arxiv.org/abs/2410.02573
Last-layer retraining methods have emerged as an efficient framework for correcting existing base models. Within this framework, several methods have been proposed to deal with correcting models for subgroup fairness with and without group membership
Externí odkaz:
http://arxiv.org/abs/2406.09561
Autor:
Freckelton, Alix V., Sebastian, Daniel, Mortier, Annelies, Triaud, Amaury H. M. J., Maxted, Pierre F. L., Acuña, Lorena, Armstrong, David J., Battley, Matthew P., Baycroft, Thomas A., Boisse, Isabelle, Bourrier, Vincent, Carmona, Andres, Coleman, Gavin A. L., Cameron, Andrew Collier, Cortés-Zuleta, Pía, Delfosse, Xavier, Dransfield, Georgina, Duck, Alison, Forveille, Thierry, French, Jenni R., Hara, Nathan, Heidari, Neda, Hellier, Coel, Kunovac, Vedad, Martin, David V., Martioli, Eder, McCormac, James J., Nelson, Richard P., Sairam, Lalitha, Sousa, Sérgio G., Standing, Matthew R., Willett, Emma
Planets orbiting binary systems are relatively unexplored compared to those around single stars. Detections of circumbinary planets and planetary systems offer a first detailed view into our understanding of circumbinary planet formation and dynamica
Externí odkaz:
http://arxiv.org/abs/2406.03094
Ensuring fair predictions across many distinct subpopulations in the training data can be prohibitive for large models. Recently, simple linear last layer retraining strategies, in combination with data augmentation methods such as upweighting, downs
Externí odkaz:
http://arxiv.org/abs/2405.05934
Distributed energy resources (DERs) such as grid-responsive loads and batteries can be harnessed to provide ramping and regulation services across the grid. This paper concerns the problem of optimal allocation of different classes of DERs, where eac
Externí odkaz:
http://arxiv.org/abs/2405.02813
Autor:
Mukherjee, Subhojyoti, Lalitha, Anusha, Kalantari, Kousha, Deshmukh, Aniket, Liu, Ge, Ma, Yifei, Kveton, Branislav
Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations, we study efficient human preference elicitation for learning preferen
Externí odkaz:
http://arxiv.org/abs/2404.13895