Search Results for author:
Found 22 papers, 3 papers with code
Randomization matters How to defend against strong adversarial attacks
We demonstrate the non-existence of a Nash equilibrium in our game when the classifier and the adversary are both deterministic, hence giving a negative answer to the above question in the deterministic regime.
Exploring Precision and Recall to assess the quality and diversity of LLMs
This paper introduces a novel evaluation framework for Large Language Models (LLMs) such as Llama-2 and Mistral, focusing on the adaptation of Precision and Recall metrics from image generation to text generation.
Optimal Budgeted Rejection Sampling for Generative Models
Rejection sampling methods have recently been proposed to improve the performance of discriminator-based generative models.
Ranked #14 on
Image Generation
on CelebA 64x64
Adversarial attacks for mixtures of classifiers
However, it has been shown that existing attacks are not well suited for this kind of classifiers.
Training Normalizing Flows with the Precision-Recall Divergence
Generative models can have distinct mode of failures like mode dropping and low quality samples, which cannot be captured by a single scalar metric.
Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis
We first show that these certificates use too little information about the classifier, and are in particular blind to the local curvature of the decision boundary.
An $α$-No-Regret Algorithm For Graphical Bilinear Bandits
We propose the first regret-based approach to the Graphical Bilinear Bandits problem, where $n$ agents in a graph play a stochastic bilinear bandit game with each of their neighbors.
Towards Consistency in Adversarial Classification
In this paper, we expose some pathological behaviors specific to the adversarial problem, and show that no convex surrogate loss can be consistent or calibrated in this context.
Asymptotic convergence rates for averaging strategies
Averaging the $\mu$ best individuals among the $\lambda$ evaluations is known to provide better estimates of the optimum of a function than just picking up the best.
On the expressivity of bi-Lipschitz normalizing flows
An invertible function is bi-Lipschitz if both the function and its inverse have bounded Lipschitz constants.
On the robustness of randomized classifiers to adversarial examples
This paper investigates the theory of robustness against adversarial attacks.
Mixed Nash Equilibria in the Adversarial Examples Game
This paper tackles the problem of adversarial examples from a game theoretic point of view.
Best Arm Identification in Graphical Bilinear Bandits
We study the best arm identification problem in which the learner wants to find the graph allocation maximizing the sum of the bilinear rewards.
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks.
On averaging the best samples in evolutionary computation
With our choice of selection rate, we get a provable regret of order $O(\lambda^{-1})$ which has to be compared with $O(\lambda^{-2/d})$ in the case where $\mu=1$.
Randomization matters. How to defend against strong adversarial attacks
We demonstrate the non-existence of a Nash equilibrium in our game when the classifier and the Adversary are both deterministic, hence giving a negative answer to the above question in the deterministic regime.
Online Trajectory Planning Through Combined Trajectory Optimization and Function Approximation: Application to the Exoskeleton Atalante
Autonomous robots require online trajectory planning capability to operate in the real world.
The Expressive Power of Deep Neural Networks with Circulant Matrices
Recent results from linear algebra stating that any matrix can be decomposed into products of diagonal and circulant matrices has lead to the design of compact deep neural network architectures that perform well in practice.
Understanding and Training Deep Diagonal Circulant Neural Networks
In this paper, we study deep diagonal circulant neural networks, that is deep neural networks in which weight matrices are the product of diagonal and circulant ones.
Training compact deep learning models for video classification using circulant matrices
In real world scenarios, model accuracy is hardly the only factor to consider.
Disease Classification in Metagenomics with 2D Embeddings and Deep Learning
Generally, when the sample size ($N$) is much bigger than the number of features ($d$), DL often outperforms other machine learning (ML) techniques, often through the use of Convolutional Neural Networks (CNNs).
Deep Learning for Metagenomic Data: using 2D Embeddings and Convolutional Neural Networks
However, in many bioinformatics ML tasks, we encounter the opposite situation where d is greater than N. In these situations, applying DL techniques (such as feed-forward networks) would lead to severe overfitting.
