• Publications
  • Influence
The Split Bregman Method for L1-Regularized Problems
TLDR
This paper proposes a “split Bregman” method, which can solve a very broad class of L1-regularized problems, and applies this technique to the Rudin-Osher-Fatemi functional for image denoising and to a compressed sensing problem that arises in magnetic resonance imaging. Expand
Fast Alternating Direction Optimization Methods
TLDR
This paper considers accelerated variants of two common alternating direction methods: the alternating direction method of multipliers (ADMM) and the alternating minimization algorithm (AMA), of the form first proposed by Nesterov for gradient descent methods. Expand
Visualizing the Loss Landscape of Neural Nets
TLDR
This paper introduces a simple "filter normalization" method that helps to visualize loss function curvature and make meaningful side-by-side comparisons between loss functions, and explores how network architecture affects the loss landscape, and how training parameters affect the shape of minimizers. Expand
Adversarial Training for Free!
TLDR
This work presents an algorithm that eliminates the overhead cost of generating adversarial examples by recycling the gradient information computed when updating model parameters, and achieves comparable robustness to PGD adversarial training on the CIFAR-10 and CIFar-100 datasets at negligible additional cost compared to natural training. Expand
Geometric Applications of the Split Bregman Method: Segmentation and Surface Reconstruction
TLDR
The primary purpose of this paper is to examine the effectiveness of “Split Bregman” techniques for solving image segmentation problems, and to compare this scheme with more conventional methods. Expand
Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
TLDR
This paper explores poisoning attacks on neural nets using "clean-labels", an optimization-based method for crafting poisons, and shows that just one single poison image can control classifier behavior when transfer learning is used. Expand
Quantized Precoding for Massive MU-MIMO
TLDR
This paper investigates the problem of downlink precoding for a narrowband massive MU-MIMO system with low-resolution digital-to-analog converters (DACs) at the base station and proposes novel nonlinear precoding algorithms that significantly outperform linear precoders at the cost of an increased computational complexity. Expand
Training Neural Networks Without Gradients: A Scalable ADMM Approach
TLDR
This paper explores an unconventional training method that uses alternating direction methods and Bregman iteration to train networks without gradient descent steps, and exhibits strong scaling in the distributed setting, yielding linear speedups even when split over thousands of cores. Expand
FreeLB: Enhanced Adversarial Training for Natural Language Understanding
TLDR
A novel adversarial training algorithm is proposed, FreeLB, that promotes higher invariance in the embedding space, by adding adversarial perturbations to word embeddings and minimizing the resultant adversarial risk inside different regions around input samples. Expand
A Field Guide to Forward-Backward Splitting with a FASTA Implementation
TLDR
FASTA provides a simple interface for applying forward-backward splitting to a broad range of problems, and issues like stepsize selection, acceleration, stopping conditions, and initialization are considered. Expand
...
1
2
3
4
5
...