Search Results for author: Julia Kempe

Found 11 papers, 4 papers with code

On the Robustness of Neural Collapse and the Neural Collapse of Robustness

no code implementations13 Nov 2023 Jingtong Su, Ya Shi Zhang, Nikolaos Tsilivis, Julia Kempe

Neural Collapse refers to the curious phenomenon in the end of training of a neural network, where feature vectors and classification weights converge to a very simple geometrical arrangement (a simplex).

Kernels, Data & Physics

no code implementations5 Jul 2023 Francesco Cagnetta, Deborah Oliveira, Mahalakshmi Sabanayagam, Nikolaos Tsilivis, Julia Kempe

Lecture notes from the course given by Professor Julia Kempe at the summer school "Statistical physics of Machine Learning" in Les Houches.

Adversarial Robustness Inductive Bias

Wavelets Beat Monkeys at Adversarial Robustness

no code implementations19 Apr 2023 Jingtong Su, Julia Kempe

2) Replacing the front-end VOneBlock by an off-the-shelf parameter-free Scatternet followed by simple uniform Gaussian noise can achieve much more substantial adversarial robustness without adversarial training.

Adversarial Attack Adversarial Robustness

What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?

1 code implementation11 Oct 2022 Nikolaos Tsilivis, Julia Kempe

The adversarial vulnerability of neural nets, and subsequent techniques to create robust models have attracted significant attention; yet we still lack a full understanding of this phenomenon.

Adversarial Robustness

ImpressLearn: Continual Learning via Combined Task Impressions

no code implementations5 Oct 2022 Dhrupad Bhardwaj, Julia Kempe, Artem Vysogorets, Angela M. Teng, Evaristus C. Ezekwem

Starting from existing work on network masking (Wortsman et al., 2020), we show that simply learning a linear combination of a small number of task-specific supermasks (impressions) on a randomly initialized backbone network is sufficient to both retain accuracy on previously learned tasks, as well as achieve high accuracy on unseen tasks.

Continual Learning Image Classification +1

Can we achieve robustness from data alone?

1 code implementation24 Jul 2022 Nikolaos Tsilivis, Jingtong Su, Julia Kempe

In parallel, we revisit prior work that also focused on the problem of data optimization for robust classification \citep{Ily+19}, and show that being robust to adversarial attacks after standard (gradient descent) training on a suitable dataset is more challenging than previously thought.

Meta-Learning regression +1

The NTK Adversary: An Approach to Adversarial Attacks without any Model Access

no code implementations29 Sep 2021 Nikolaos Tsilivis, Julia Kempe

In particular, in the regime where the Neural Tangent Kernel theory holds, we derive a simple, but powerful strategy for attacking models, which in contrast to prior work, does not require any access to the model under attack, or any trained replica of it for that matter.

Learning Theory

Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity

1 code implementation5 Jul 2021 Artem Vysogorets, Julia Kempe

Neural network pruning is a fruitful area of research with surging interest in high sparsity regimes.

Benchmarking Network Pruning

Quantum random walks - an introductory overview

1 code implementation13 Mar 2003 Julia Kempe

This article aims to provide an introductory survey on quantum random walks.

Quantum Physics Data Structures and Algorithms

Quantum Walks On Graphs

no code implementations18 Dec 2000 Dorit Aharonov, Andris Ambainis, Julia Kempe, Umesh Vazirani

We set the ground for a theory of quantum walks on graphs- the generalization of random walks on finite graphs to the quantum world.

Quantum Physics

Universal simulation of Markovian quantum dynamics

no code implementations15 Aug 2000 Dave Bacon, Andrew M. Childs, Isaac L. Chuang, Julia Kempe, Debbie W. Leung, Xinlan Zhou

Although the conditions for performing arbitrary unitary operations to simulate the dynamics of a closed quantum system are well understood, the same is not true of the more general class of quantum operations (also known as superoperators) corresponding to the dynamics of open quantum systems.

Quantum Physics

Cannot find the paper you are looking for? You can Submit a new open access paper.