14 citations · 36 across the 15 of their papers we have counts for
16 papers
Efficient Learning of Truncated Boolean Product Distributions: Influence to the Rescue
Rohan Chauhan, Ioannis Panageas
Learning the natural parameters of discrete distributions from independent samples constrained to a subset is a foundational chal…
The Complexity of Finding Local Optima in Contrastive Learning
Jingming Yan, Yiyuan Luo, Vaggos Chatziafratis +3
Contrastive learning is a powerful technique for discovering meaningful data representations by optimizing objectives based on , often given as a…
Learning the Inverse Temperature of Ising Models under Hard Constraints using One Sample
Rohan Chauhan, Ioannis Panageas
We consider the problem of estimating inverse temperature parameter of an -dimensional truncated Ising model using a single sample. Given a graph with vertic…
Last-iterate Convergence Separation between Extra-gradient and Optimism in Constrained Periodic Games
Yi Feng, Ping Li, Ioannis Panageas +1
Last-iterate behaviors of learning algorithms in repeated two-player zero-sum games have been extensively studied due to their wide applications in machine learning and related tas…
Polynomial Convergence of Bandit No-Regret Dynamics in Congestion Games
Leello Dadi, Ioannis Panageas, Stratis Skoulakis +2
We introduce an online learning algorithm in the bandit feedback model that, once adopted by all agents of a congestion game, results in game-dynamics that converge to an -appro…
On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails
Yi Feng, Hu Fu, Qun Hu +4
Last-iterate convergence has received extensive study in two player zero-sum games starting from bilinear, convex-concave up to settings that satisfy the MVI condition. Typical met…
Semi Bandit Dynamics in Congestion Games: Convergence to Nash Equilibrium and No-Regret Guarantees
Ioannis Panageas, Stratis Skoulakis, Luca Viano +2
In this work, we introduce a new variant of online gradient descent, which provably converges to Nash Equilibria and simultaneously attains sublinear regret for the class of conges…
On Scrambling Phenomena for Randomly Initialized Recurrent Networks
Vaggos Chatziafratis, Ioannis Panageas, Clayton Sanford +1
Recurrent Neural Networks (RNNs) frequently exhibit complicated dynamics, and their sensitivity to the initialization process often renders them notoriously hard to train. Recent w…
Accelerated Multiplicative Weights Update Avoids Saddle Points almost always
Yi Feng, Ioannis Panageas, Xiao Wang
We consider non-convex optimization problems with constraint that is a product of simplices. A commonly used algorithm in solving this type of problem is the Multiplicative Weights…
Fast Convergence of Langevin Dynamics on Manifold: Geodesics meet Log-Sobolev
Xiao Wang, Qi Lei, Ioannis Panageas
Sampling is a fundamental and arguably very important task with numerous applications in Machine Learning. One approach to sample from a high dimensional distribution for…
Efficient Statistics for Sparse Graphical Models from Truncated Samples
Arnab Bhattacharyya, Rathin Desai, Sai Ganesh Nagarajan +1
In this paper, we study high-dimensional estimation from truncated samples. We focus on two fundamental and classical problems: (i) inference of sparse Gaussian graphical models an…
Convergence to Second-Order Stationarity for Non-negative Matrix Factorization: Provably and Concurrently
Ioannis Panageas, Stratis Skoulakis, Antonios Varvitsiotis +1
Non-negative matrix factorization (NMF) is a fundamental non-convex optimization problem with numerous applications in Machine Learning (music analysis, document clustering, speech…
Better Depth-Width Trade-offs for Neural Networks through the lens of Dynamical Systems
Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas
The expressivity of neural networks as a function of their depth, width and type of activation units has been an important question in deep learning theory. Recently, depth separat…
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
Qi Lei, Sai Ganesh Nagarajan, Ioannis Panageas +1
In a recent series of papers it has been established that variants of Gradient Descent/Ascent and Mirror Descent exhibit last iterate convergence in convex-concave zero-sum games.…
Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem
Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas +1
Understanding the representational power of Deep Neural Networks (DNNs) and how their structural properties (e.g., depth, width, type of activation unit) affect the functions they…
On the Analysis of EM for truncated mixtures of two Gaussians
Sai Ganesh Nagarajan, Ioannis Panageas
Motivated by a recent result of Daskalakis et al. 2018, we analyze the population version of Expectation-Maximization (EM) algorithm for the case of \textit{truncated} mixtures of…