Pratik Chaudhari
Pratik Chaudhari
University of Pennsylvania
Email verificata su ucla.edu - Home page
TitoloCitata daAnno
Entropy-SGD: biasing gradient descent into wide valleys
P Chaudhari, A Choromanska, S Soatto, Y LeCun, C Baldassi, C Borgs, ...
arXiv preprint arXiv:1611.01838, 2016
1862016
Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks
P Chaudhari, S Soatto
2018 Information Theory and Applications Workshop (ITA), 1-10, 2018
662018
Deep relaxation: partial differential equations for optimizing deep neural networks
P Chaudhari, A Oberman, S Osher, S Soatto, G Carlier
Research in the Mathematical Sciences 5 (3), 30, 2018
542018
Incremental sampling-based algorithm for minimum-violation motion planning
LIR Castro, P Chaudhari, J Tůmov, S Karaman, E Frazzoli, D Rus
52nd IEEE Conference on Decision and Control, 3217-3224, 2013
492013
Sampling-based algorithms for continuous-time POMDPs
P Chaudhari, S Karaman, D Hsu, E Frazzoli
2013 American Control Conference, 4604-4610, 2013
222013
On the energy landscape of deep networks
P Chaudhari, S Soatto
arXiv:1511.06485, 2015
19*2015
Parle: parallelizing stochastic gradient descent
P Chaudhari, C Baldassi, R Zecchina, S Soatto, A Talwalkar, A Oberman
arXiv preprint arXiv:1707.00424, 2017
132017
Game theoretic controller synthesis for multi-robot motion planning Part I: Trajectory based algorithms
M Zhu, M Otte, P Chaudhari, E Frazzoli
2014 IEEE International Conference on Robotics and Automation (ICRA), 1646-1651, 2014
122014
Sampling-based algorithms for optimal motion planning using process algebra specifications
V Varricchio, P Chaudhari, E Frazzoli
2014 IEEE International Conference on Robotics and Automation (ICRA), 5326-5332, 2014
92014
Incremental minimum-violation control synthesis for robots interacting with external agents
P Chaudhari, T Wongpiromsarny, E Frazzoli
2014 American Control Conference, 1761-1768, 2014
62014
Sampling-based algorithm for filtering using Markov chain approximations
P Chaudhari, S Karaman, E Frazzoli
2012 IEEE 51st IEEE Conference on Decision and Control (CDC), 5972-5978, 2012
52012
Localization using Average Landmark Vector in the presence of clutter
P Chaudhari
2009 World Congress on Nature & Biologically Inspired Computing (NaBIC…, 2009
22009
P3O: Policy-on Policy-off Policy Optimization
R Fakoor, P Chaudhari, AJ Smola
arXiv preprint arXiv:1905.01756, 2019
2019
Approximate POMDP homomorphisms
P Chaudhari
2014
Algorithms for autonomous urban navigation with formal specifications
P Chaudhari
Massachusetts Institute of Technology, 2014
2014
Incremental sampling based algorithms for state estimation
P Chaudhari
Massachusetts Institute of Technology, 2012
2012
Il sistema al momento non pu eseguire l'operazione. Riprova pi tardi.
Articoli 1–16