activity
20212024
most citedProjected Randomized Smoothing for Certified Adversarial Robustness

3 citations · 9 across the 12 of their papers we have counts for

collaborators

12 papers

math.OC2024

Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses

Ziye Ma, Ying Chen, Javad Lavaei +1

Matrix sensing problems exhibit pervasive non-convexity, plaguing optimization with a proliferation of suboptimal spurious solutions. Avoiding convergence to these critical points…

cs.CV2024

Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding

Yatong Bai, Utsav Garg, Apaar Shanker +10

Vision and vision-language applications of neural networks, such as image classification and captioning, rely on large-scale annotated datasets that require non-trivial data-collec…

cs.LG2023

Tempo Adaptation in Non-stationary Reinforcement Learning

Hyunin Lee, Yuhao Ding, Jongmin Lee +3

We first raise and tackle a ``time synchronization'' issue between the agent and the environment in non-stationary reinforcement learning (RL), a crucial factor hindering its real-…

math.OC20231 cited

Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing

Ziye Ma, Javad Lavaei, Somayeh Sojoudi

Gradient descent (GD) is crucial for generalization in machine learning models, as it induces implicit regularization, promoting compact representations. In this work, we examine t…

math.OC2023

Tight Certified Robustness via Min-Max Representations of ReLU Neural Networks

Brendon G. Anderson, Samuel Pfrommer, Somayeh Sojoudi

The reliable deployment of neural networks in control systems requires rigorous robustness guarantees. In this paper, we obtain tight robustness certificates over convex attack set…

cs.LG20232 cited

Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization

Tanmay Gautam, Reid Pryzant, Ziyi Yang +2

Vector Quantization (VQ) is a well-known technique in deep learning for extracting informative discrete latent representations. VQ-embedded models have shown impressive results in…