papers

Publications (9)

cs.CV2022

What do Vision Transformers Learn? A Visual Exploration

Amin Ghiasi, Hamid Kazemi, Eitan Borgnia +5

Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing…

cs.CV2022

A Deep Dive into Dataset Imbalance and Bias in Face Identification

Valeriia Cherepanova, Steven Reich, Samuel Dooley +3

As the deployment of automated face recognition (FR) systems proliferates, bias in these systems is not just an academic question, but a matter of public concern. Media portrayals…

math.NT2020

Class Group Relations in a Function Field Analogue of

Steven Reich

For an odd prime and polynomial , we consider the extension of defined by adjoining a root of . Such a field is a function field ana…

cs.LG2019

WITCHcraft: Efficient PGD attacks with random step size

Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum +4

State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods wit…

q-bio.NC2012

The impact of short term synaptic depression and stochastic vesicle dynamics on neural variability

Steven Reich, Robert Rosenbaum

Neural variability plays a central role in neural coding and neuronal network dynamics. Unreliability of synaptic transmission is a major source of neural variability: synaptic neu…

cs.LG2020

Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks

Micah Goldblum, Steven Reich, Liam Fowl +3

Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods,…

cs.CV2022

Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations

Amin Ghiasi, Hamid Kazemi, Steven Reich +3

Existing techniques for model inversion typically rely on hard-to-tune regularizers, such as total variation or feature regularization, which must be individually calibrated for ea…

cs.LG2021

Ensemble Distillation for Structured Prediction: Calibrated, Accurate, Fast-Choose Three

Steven Reich, David Mueller, Nicholas Andrews

Modern neural networks do not always produce well-calibrated predictions, even when trained with a proper scoring function such as cross-entropy. In classification settings, simple…

cs.LG2023

Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models

Liam Fowl, Jonas Geiping, Steven Reich +4

A central tenet of Federated learning (FL), which trains models without centralizing user data, is privacy. However, previous work has shown that the gradient updates used in FL ca…