Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Gugan Thoppe"'
Publikováno v:
Discrete Analysis (2023)
The Shadow Knows: Empirical Distributions of Minimal Spanning Acycles and Persistence Diagrams of Random Complexes, Discrete Analysis 2023:2, 18 pp. This paper deals with the following natural and important question. Suppose that the edges of the co
Externí odkaz:
https://doaj.org/article/0df2cfac620f4a0f9328c2e559b7df1c
We consider the measurement model $Y = AX,$ where $X$ and, hence, $Y$ are random variables and $A$ is an a priori known tall matrix. At each time instance, a sample of one of $Y$'s coordinates is available, and the goal is to estimate $\mu := \mathbb
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c6dc0dd862186cf2287d8a85d88465f
Autor:
Gugan Thoppe, Bhumesh Kumar
In Multi-Agent Reinforcement Learning (MARL), multiple agents interact with a common environment, as also with each other, for solving a shared problem in sequential decision-making. It has wide-ranging applications in gaming, robotics, finance, etc.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0aeeb024d20e71d4e883c800d65b2780
http://arxiv.org/abs/2110.15092
http://arxiv.org/abs/2110.15092
Autor:
Vivek S. Borkar, Gugan Thoppe
Publikováno v:
Stochastic Systems. 9:1-26
Given an ordinary differential equation (ODE) and its perturbation, the Alekseev formula expresses the solutions of the latter in terms related to the former. By exploiting this formula and a new concentration inequality for martingale-differences, w
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5bfbbe69178acfb93aba8089d5a04e46
https://doi.org/10.1287/stsy.2018.0019
https://doi.org/10.1287/stsy.2018.0019
Publikováno v:
VALUETOOLS 2020-13th EAI International Conference on Performance Evaluation Methodologies and Tools
VALUETOOLS 2020-13th EAI International Conference on Performance Evaluation Methodologies and Tools, May 2020, Tsukuba, Japan
VALUETOOLS
HAL
VALUETOOLS 2020-13th EAI International Conference on Performance Evaluation Methodologies and Tools, May 2020, Tsukuba, Japan
VALUETOOLS
HAL
For providing quick and accurate results, a search engine maintains a local snapshot of the entire web. And, to keep this local cache fresh, it employs a crawler for tracking changes across various web pages. However, finite bandwidth availability an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8bb36437f08583dc9b6652898b4a72d3
https://hal.inria.fr/hal-03123809
https://hal.inria.fr/hal-03123809
Topological study of existing random simplicial complexes is non-trivial and has led to several seminal works. However, the applicability of such studies is limited since the randomness there is usually governed by a single parameter. With this in mi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::96ca801d42b6a51f2a2e18b975ce4f1f
http://arxiv.org/abs/2001.06860
http://arxiv.org/abs/2001.06860
Publikováno v:
Performance Evaluation
Performance Evaluation, 2022, SI: ValueTools 2020, 153, pp.25. ⟨10.1016/j.peva.2021.102261⟩
Performance Evaluation, Elsevier, 2021, SI: ValueTools 2020, 153, ⟨10.1016/j.peva.2021.102261⟩
Performance Evaluation, 2022, SI: ValueTools 2020, 153, pp.25. ⟨10.1016/j.peva.2021.102261⟩
Performance Evaluation, Elsevier, 2021, SI: ValueTools 2020, 153, ⟨10.1016/j.peva.2021.102261⟩
A search engine maintains local copies of different web pages to provide quick search results. This local cache is kept up-to-date by a web crawler that frequently visits these different pages to track changes in them. Ideally, the local copy should
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c4965715c580b23fcd68b60799beb09
Publikováno v:
AAAI
Policy evaluation in reinforcement learning is often conducted using two-timescale stochastic approximation, which results in various gradient temporal difference methods such as GTD(0), GTD2, and TDC. Here, we provide convergence rate bounds for thi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d037fa24422a3009b85d5c53b5f49c98
http://arxiv.org/abs/1911.09157
http://arxiv.org/abs/1911.09157
A weighted $d-$complex is a simplicial complex of dimension $d$ in which each face is assigned a real-valued weight. We derive three key results here concerning persistence diagrams and minimal spanning acycles (MSAs) of such complexes. First, we est
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bdf84be7695fea519b38239a4a9df213
Autor:
Vivek S. Borkar, Gugan Thoppe
Publikováno v:
ITA
This is a summary of the main results of [9] concerning concentration of interpolated iterates of a Robbins-Monro scheme around the trajectory of a limiting differential equation from some time on.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c2dfc93f205bde347172e80f8485ddfd
https://doi.org/10.1109/ita.2016.7888205
https://doi.org/10.1109/ita.2016.7888205