Zobrazeno 1 - 10
of 39
pro vyhledávání: '"Thopalli, Kowshik"'
LLM-based data generation for real-world tabular data can be challenged by the lack of sufficient semantic context in feature names used to describe columns. We hypothesize that enriching prompts with domain-specific insights can improve both the qua
Externí odkaz:
http://arxiv.org/abs/2409.03946
Reliably detecting when a deployed machine learning model is likely to fail on a given input is crucial for ensuring safe operation. In this work, we propose DECIDER (Debiasing Classifiers to Identify Errors Reliably), a novel approach that leverages
Externí odkaz:
http://arxiv.org/abs/2408.00331
Scaling up neural networks has been a key recipe to the success of large language and vision models. However, in practice, up-scaled models can be disproportionately costly in terms of computations, providing only marginal improvements in performance
Externí odkaz:
http://arxiv.org/abs/2406.17117
Autor:
Narayanaswamy, Vivek, Thopalli, Kowshik, Anirudh, Rushil, Mubarka, Yamen, Sakla, Wesam, Thiagarajan, Jayaraman J.
Anchoring is a recent, architecture-agnostic principle for training deep neural networks that has been shown to significantly improve uncertainty estimation, calibration, and extrapolation capabilities. In this paper, we systematically explore anchor
Externí odkaz:
http://arxiv.org/abs/2406.00529
In this paper, we address the problem of adapting models from a source domain to a target domain, a task that has become increasingly important due to the brittle generalization of deep neural networks. While several test-time adaptation techniques h
Externí odkaz:
http://arxiv.org/abs/2305.13284
Autor:
Subramanyam, Rakshith, Thopalli, Kowshik, Berman, Spring, Turaga, Pavan, Thiagarajan, Jayaraman J.
The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation techniques have emerged, they ty
Externí odkaz:
http://arxiv.org/abs/2210.16692
A foundational requirement of a deployed ML model is to generalize to data drawn from a testing distribution that is different from training. A popular solution to this problem is to adapt a pre-trained model to novel domains using only unlabeled dat
Externí odkaz:
http://arxiv.org/abs/2207.04185
Unsupervised domain adaptation (UDA) aims to transfer and adapt knowledge from a labeled source domain to an unlabeled target domain. Traditionally, subspace-based methods form an important class of solutions to this problem. Despite their mathematic
Externí odkaz:
http://arxiv.org/abs/2201.01806
Domain generalization (DG) methods aim to develop models that generalize to settings where the test distribution is different from the training data. In this paper, we focus on the challenging problem of multi-source zero shot DG (MDG), where labeled
Externí odkaz:
http://arxiv.org/abs/2112.09802
Autor:
Seymour, Zachary, Thopalli, Kowshik, Mithun, Niluthpol, Chiu, Han-Pang, Samarasekera, Supun, Kumar, Rakesh
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this task; howev
Externí odkaz:
http://arxiv.org/abs/2103.11374