Zobrazeno 1 - 10
of 58
pro vyhledávání: '"Nagaraj, Dheeraj"'
We consider the problem of high-dimensional heavy-tailed statistical estimation in the streaming setting, which is much harder than the traditional batch setting due to memory constraints. We cast this problem as stochastic convex optimization with h
Externí odkaz:
http://arxiv.org/abs/2410.20135
Applying Reinforcement Learning (RL) to Restless Multi-Arm Bandits (RMABs) offers a promising avenue for addressing allocation problems with resource constraints and temporal dynamics. However, classic RMAB models largely overlook the challenges of (
Externí odkaz:
http://arxiv.org/abs/2408.05686
Autor:
Kandasamy, Saravanan, Nagaraj, Dheeraj
Langevin Dynamics is a Stochastic Differential Equation (SDE) central to sampling and generative modeling and is implemented via time discretization. Langevin Monte Carlo (LMC), based on the Euler-Maruyama discretization, is the simplest and most stu
Externí odkaz:
http://arxiv.org/abs/2405.17068
We introduce the Glauber Generative Model (GGM), a new class of discrete diffusion models, to obtain new samples from a distribution given samples from a discrete space. GGM deploys a discrete Markov chain called the heat bath dynamics (or the Glaube
Externí odkaz:
http://arxiv.org/abs/2405.17035
Restless multi-armed bandits (RMAB) have demonstrated success in optimizing resource allocation for large beneficiary populations in public health settings. Unfortunately, RMAB models lack flexibility to adapt to evolving public health policy priorit
Externí odkaz:
http://arxiv.org/abs/2402.14807
Autor:
Zhao, Yunfan, Behari, Nikhil, Hughes, Edward, Zhang, Edwin, Nagaraj, Dheeraj, Tuyls, Karl, Taneja, Aparna, Tambe, Milind
Restless multi-arm bandits (RMABs), a class of resource allocation problems with broad application in areas such as healthcare, online advertising, and anti-poaching, have recently been studied from a multi-agent reinforcement learning perspective. P
Externí odkaz:
http://arxiv.org/abs/2310.14526
We consider the problem of heteroscedastic linear regression, where, given $n$ samples $(\mathbf{x}_i, y_i)$ from $y_i = \langle \mathbf{w}^{*}, \mathbf{x}_i \rangle + \epsilon_i \cdot \langle \mathbf{f}^{*}, \mathbf{x}_i \rangle$ with $\mathbf{x}_i
Externí odkaz:
http://arxiv.org/abs/2306.14288
We present Re-weighted Gradient Descent (RGD), a novel optimization technique that improves the performance of deep neural networks through dynamic sample re-weighting. Leveraging insights from distributionally robust optimization (DRO) with Kullback
Externí odkaz:
http://arxiv.org/abs/2306.09222
Autor:
Das, Aniket, Nagaraj, Dheeraj
Stein Variational Gradient Descent (SVGD) is a popular variational inference algorithm which simulates an interacting particle system to approximately sample from a target distribution, with impressive empirical performance across various domains. Th
Externí odkaz:
http://arxiv.org/abs/2305.17558
Autor:
Nagaraj, Dheeraj M.
Networks are used ubiquitously to model global phenomena which emerge due to interactions between multiple agents and are among the objects of fundamental interest in machine learning. The purpose of this dissertation is to understand expressivity an
Externí odkaz:
https://hdl.handle.net/1721.1/143250