Zobrazeno 1 - 10
of 98
pro vyhledávání: '"Baranwal, Mayank"'
Autor:
Chakrabarti, Kushal, Baranwal, Mayank
Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are not as well understood as vani
Externí odkaz:
http://arxiv.org/abs/2407.12629
A chemical reaction mechanism (CRM) is a sequence of molecular-level events involving bond-breaking/forming processes, generating transient intermediates along the reaction pathway as reactants transform into products. Understanding such mechanisms i
Externí odkaz:
http://arxiv.org/abs/2407.10090
Autor:
Chakrabarti, Kushal, Baranwal, Mayank
This paper considers solving distributed convex optimization problems in peer-to-peer multi-agent networks. The network is assumed to be synchronous and connected. By using the proportional-integral (PI) control strategy, various algorithms with fixe
Externí odkaz:
http://arxiv.org/abs/2310.00419
Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks. Motivated by the recent advances in fixed-time stability theory of continuous-time dynamical systems, w
Externí odkaz:
http://arxiv.org/abs/2212.03765
Power grids, across the world, play an important societal and economical role by providing uninterrupted, reliable and transient-free power to several industries, businesses and household consumers. With the advent of renewable power resources and EV
Externí odkaz:
http://arxiv.org/abs/2212.02397
Autor:
Garg, Kunal, Baranwal, Mayank
This study develops a fixed-time convergent saddle point dynamical system for solving min-max problems under a relaxation of standard convexity-concavity assumption. In particular, it is shown that by leveraging the dynamical systems viewpoint of an
Externí odkaz:
http://arxiv.org/abs/2207.12845
Most existing literature on supply chain and inventory management consider stochastic demand processes with zero or constant lead times. While it is true that in certain niche scenarios, uncertainty in lead times can be ignored, most real-world scena
Externí odkaz:
http://arxiv.org/abs/2203.00885
Accelerated gradient methods are the cornerstones of large-scale, data-driven optimization problems that arise naturally in machine learning and other fields concerning data analysis. We introduce a gradient-based optimization framework for achieving
Externí odkaz:
http://arxiv.org/abs/2112.01363
Autor:
Baranwal, Mayank, Saldinger, Jacob C., Kim, Doohyun, Elvati, Paolo, Hero, Alfred O., Violi, Angela
Publikováno v:
In Fuel 1 July 2024 367
Several real-world scenarios, such as remote control and sensing, are comprised of action and observation delays. The presence of delays degrades the performance of reinforcement learning (RL) algorithms, often to such an extent that algorithms fail
Externí odkaz:
http://arxiv.org/abs/2108.07555