Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Malviya, Pranshu"'
The optimal model for a given task is often challenging to determine, requiring training multiple models from scratch which becomes prohibitive as dataset and model sizes grow. A more efficient alternative is to reuse smaller pre-trained models by ex
Externí odkaz:
http://arxiv.org/abs/2405.15895
Sharpness-aware minimization (SAM) methods have gained increasing popularity by formulating the problem of minimizing both loss value and loss sharpness as a minimax objective. In this work, we increase the efficiency of the maximization and minimiza
Externí odkaz:
http://arxiv.org/abs/2307.16704
Autor:
Malviya, Pranshu, Mordido, Gonçalo, Baratin, Aristide, Harikandeh, Reza Babanezhad, Huang, Jerry, Lacoste-Julien, Simon, Pascanu, Razvan, Chandar, Sarath
Adaptive gradient-based optimizers, notably Adam, have left their mark in training large-scale deep learning models, offering fast convergence and robustness to hyperparameter settings. However, they often struggle with generalization, attributed to
Externí odkaz:
http://arxiv.org/abs/2307.09638
Many studies on scaling laws consider basic factors such as model size, model shape, dataset size, and compute power. These factors are easily tunable and represent the fundamental elements of any machine learning setup. But researchers have also emp
Externí odkaz:
http://arxiv.org/abs/2209.01275
Autor:
Sodhani, Shagun, Faramarzi, Mojtaba, Mehta, Sanket Vaibhav, Malviya, Pranshu, Abdelsalam, Mohamed, Janarthanan, Janarthanan, Chandar, Sarath
This primer is an attempt to provide a detailed summary of the different facets of lifelong learning. We start with Chapter 2 which provides a high-level overview of lifelong learning systems. In this chapter, we discuss prominent scenarios in lifelo
Externí odkaz:
http://arxiv.org/abs/2207.04354
In budget-constrained settings aimed at mitigating unfairness, like law enforcement, it is essential to prioritize the sources of unfairness before taking measures to mitigate them in the real world. Unlike previous works, which only serve as a cauti
Externí odkaz:
http://arxiv.org/abs/2111.14348
When an agent encounters a continual stream of new tasks in the lifelong learning setting, it leverages the knowledge it gained from the earlier tasks to help learn the new tasks better. In such a scenario, identifying an efficient knowledge represen
Externí odkaz:
http://arxiv.org/abs/2105.05155
Minesweeper is a popular spatial-based decision-making game that works with incomplete information. As an exemplary NP-complete problem, it is a major area of research employing various artificial intelligence paradigms. The present work models this
Externí odkaz:
http://arxiv.org/abs/2105.04120
Law enforcement must prioritize sources of unfairness before mitigating their underlying unfairness, considering that they have limited resources. Unlike previous works that only make cautionary claims of discrimination and de-biases data after its g
Externí odkaz:
http://arxiv.org/abs/2007.05516
Publikováno v:
2018 Second International Conference on Advances in Electronics, Computers and Communications (ICAECC)
A contextual care protocol is used by a medical practitioner for patient healthcare, given the context or situation that the specified patient is in. This paper proposes a method to build an automated self-adapting protocol which can help make releva
Externí odkaz:
http://arxiv.org/abs/1811.06437