34 citations · 136 across the 27 of their papers we have counts for
8 papers · 1 filter
Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
Sean Gunn, Jorio Cocola, Oliver De Candido +2
Latent generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals at a single, fixed complexity, go…
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…
Accelerating data-driven algorithm selection for combinatorial partitioning problems
Vaggos Chatziafratis, Ishani Karmarkar, Yingxi Li +1
Data-driven algorithm selection is a powerful approach for choosing effective heuristics for computational problems. It operates by evaluating a set of candidate algorithms on a co…
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…
Expressivity of Neural Networks via Chaotic Itineraries beyond Sharkovsky's Theorem
Clayton Sanford, Vaggos Chatziafratis
Given a target function , how large must a neural network be in order to approximate ? Recent works examine this basic question on neural network \textit{expressivity} from t…
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…
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 Computational Power of Online Gradient Descent
Vaggos Chatziafratis, Tim Roughgarden, Joshua R. Wang
We prove that the evolution of weight vectors in online gradient descent can encode arbitrary polynomial-space computations, even in very simple learning settings. Our results impl…