Projects

Are adversarial examples inevitable?

A pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at generating robust defenses, we are led to ask a fundamental question: Are adversarial attacks inevitable?

Continue reading

Stacked U-Nets: A simple architecture for image segmentation

Stacked U-Nets are simple, easy-to-train neural architecture for image segmentation and other image-to-image regression tasks. SUNets attain state of the art performance and fast inference with very few parameters.

Continue reading

Poison Frogs! Targeted Poisoning Attacks on Neural Networks

Data poisoning is an adversarial attack in which examples are added to the training set of a classifier to manipulate the behavior of the model at test time. We propose a new poisoning attack that is effective on neural nets, and can be executed by an outsider with no control over the training process.

Continue reading

Visualizing the Loss Landscape of Neural Nets

It is well known that certain neural network architectures produce loss functions that train easier and generalize better, but the reasons for this are not well understood. To understand this better, we explore the structure of neural loss functions using a range of visualization methods.

Continue reading

Stabilizing GANs with Prediction

Adversarial networks are notoriously hard to train, and simple training methods often collapse. We present a simple modification to the standard training method that increases stability. The method is provably stable for a class of saddle-point problems, and improves performance of numerous GANs.

Continue reading

PhasePack

PhasePack is a software library that implements a wide range of different phase retrieval algorithms and initialization methods. It can also produce comparisons between algorithms, and comes with empirical datasets for testing on real-world problems.

Continue reading

Training Quantized Nets: A Deeper Understanding

Neural net parameters can often be compressed down to just one single bit without a significant loss in network performance, yielding a huge reduction in memory footprint and computational workload. We develop a theory of quantized nets, and explain the performance of algorithms for weight quantization.

Continue reading

PhaseMax

A number of non-convex optimization problems can be convexified by “lifting” strategies. These methods yield convex formulations at the cost of substantially increased dimensionality. PhaseMax is a new type of convex relaxation that does not require lifting; it solves problems in their original low-dimensional parameter space.

Continue reading

Distributed Machine Learning

Classical machine learning methods, include stochastic gradient descent (aka backprop), work great on one machine, but don’t scale well to the cloud or cluster setting. We propose a variety of algorithmic frameworks for scaling machine learning across many workers.

Continue reading

FASTA

FASTA (Fast Adaptive Shrinkage/ Thresholding Algorithm) is an efficient, easy-to-use implementation of the Forward-Backward Splitting (FBS) method (also known as the proximal gradient method) for regularized optimization problems. Many variations on FBS are available in FASTA, including the popular accelerated variant FISTA (Beck and Teboulle ’09), the adaptive stepsize rule SpaRSA

Continue reading