Alert button
Picture for Sridhar Mahadevan

Sridhar Mahadevan

Alert button

Global Convergence to the Equilibrium of GANs using Variational Inequalities

Sep 11, 2018
Ian Gemp, Sridhar Mahadevan

Figure 1 for Global Convergence to the Equilibrium of GANs using Variational Inequalities
Figure 2 for Global Convergence to the Equilibrium of GANs using Variational Inequalities
Figure 3 for Global Convergence to the Equilibrium of GANs using Variational Inequalities
Figure 4 for Global Convergence to the Equilibrium of GANs using Variational Inequalities
Viaarxiv icon

A Unified Framework for Domain Adaptation using Metric Learning on Manifolds

Apr 28, 2018
Sridhar Mahadevan, Bamdev Mishra, Shalini Ghosh

Figure 1 for A Unified Framework for Domain Adaptation using Metric Learning on Manifolds
Figure 2 for A Unified Framework for Domain Adaptation using Metric Learning on Manifolds
Figure 3 for A Unified Framework for Domain Adaptation using Metric Learning on Manifolds
Figure 4 for A Unified Framework for Domain Adaptation using Metric Learning on Manifolds
Viaarxiv icon

Online Monotone Games

Oct 19, 2017
Ian Gemp, Sridhar Mahadevan

Figure 1 for Online Monotone Games
Figure 2 for Online Monotone Games
Figure 3 for Online Monotone Games
Figure 4 for Online Monotone Games
Viaarxiv icon

Inverting Variational Autoencoders for Improved Generative Accuracy

Aug 24, 2017
Ian Gemp, Ishan Durugkar, Mario Parente, M. Darby Dyar, Sridhar Mahadevan

Figure 1 for Inverting Variational Autoencoders for Improved Generative Accuracy
Figure 2 for Inverting Variational Autoencoders for Improved Generative Accuracy
Figure 3 for Inverting Variational Autoencoders for Improved Generative Accuracy
Figure 4 for Inverting Variational Autoencoders for Improved Generative Accuracy
Viaarxiv icon

A Manifold Approach to Learning Mutually Orthogonal Subspaces

Mar 08, 2017
Stephen Giguere, Francisco Garcia, Sridhar Mahadevan

Figure 1 for A Manifold Approach to Learning Mutually Orthogonal Subspaces
Figure 2 for A Manifold Approach to Learning Mutually Orthogonal Subspaces
Figure 3 for A Manifold Approach to Learning Mutually Orthogonal Subspaces
Figure 4 for A Manifold Approach to Learning Mutually Orthogonal Subspaces
Viaarxiv icon

Generative Multi-Adversarial Networks

Mar 02, 2017
Ishan Durugkar, Ian Gemp, Sridhar Mahadevan

Figure 1 for Generative Multi-Adversarial Networks
Figure 2 for Generative Multi-Adversarial Networks
Figure 3 for Generative Multi-Adversarial Networks
Figure 4 for Generative Multi-Adversarial Networks
Viaarxiv icon

Online Monotone Optimization

Aug 29, 2016
Ian Gemp, Sridhar Mahadevan

Figure 1 for Online Monotone Optimization
Figure 2 for Online Monotone Optimization
Figure 3 for Online Monotone Optimization
Figure 4 for Online Monotone Optimization
Viaarxiv icon

Deep Reinforcement Learning With Macro-Actions

Jun 15, 2016
Ishan P. Durugkar, Clemens Rosenbaum, Stefan Dernbach, Sridhar Mahadevan

Figure 1 for Deep Reinforcement Learning With Macro-Actions
Figure 2 for Deep Reinforcement Learning With Macro-Actions
Figure 3 for Deep Reinforcement Learning With Macro-Actions
Viaarxiv icon

Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds

Jul 28, 2015
Sridhar Mahadevan, Sarath Chandar

Figure 1 for Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds
Figure 2 for Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds
Figure 3 for Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds
Figure 4 for Reasoning about Linguistic Regularities in Word Embeddings using Matrix Manifolds
Viaarxiv icon

Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces

May 26, 2014
Sridhar Mahadevan, Bo Liu, Philip Thomas, Will Dabney, Steve Giguere, Nicholas Jacek, Ian Gemp, Ji Liu

Figure 1 for Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces
Figure 2 for Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces
Figure 3 for Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces
Figure 4 for Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces
Viaarxiv icon