Search Results for author:
Found 39 papers, 9 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.
Differentially Private Gradient Flow based on the Sliced Wasserstein Distance for Non-Parametric Generative Modeling
Safeguarding privacy in sensitive training data is paramount, particularly in the context of generative modeling.
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.
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.
Non parametric estimation of causal populations in a counterfactual scenario
A Causal Auto-Encoder (CAE), enhanced by a prior dependent on treatment and outcome information, assimilates the latent space to the probability distribution of the target populations.
Two-sided fairness in rankings via Lorenz dominance
Our experiments also show that it increases the utility of the worse-off at lower costs in terms of overall utility.
Online Selection of Diverse Committees
Citizens' assemblies need to represent subpopulations according to their proportions in the general population.
Online certification of preference-based fairness for personalized recommender systems
We propose to audit for envy-freeness, a more granular criterion aligned with individual preferences: every user should prefer their recommendations to those of other users.
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.
AAMDRL: Augmented Asset Management with Deep Reinforcement Learning
Can an agent learn efficiently in a noisy and self adapting environment with sequential, non-stationary and non-homogeneous observations?
Detecting and adapting to crisis pattern with context based Deep Reinforcement Learning
Deep reinforcement learning (DRL) has reached super human levels in complex tasks like game solving (Go and autonomous driving).
On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory
This paper tackles the problem of Lipschitz regularization of Convolutional Neural Networks.
Equitable and Optimal Transport with Multiple Agents
When there is only one agent, we recover the Optimal Transport problem.
Estimating Individual Treatment Effects through Causal Populations Identification
Estimating the Individual Treatment Effect from observational data, defined as the difference between outcomes with and without treatment or intervention, while observing just one of both, is a challenging problems in causal learning.
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.
Yet another but more efficient black-box adversarial attack: tiling and evolution strategies
In the targeted setting, we are able to reach, with a limited budget of $100, 000$, $100\%$ of success rate with a budget of $6, 662$ queries on average, i. e. we need $800$ queries less than the current state of the art.
A unified view on differential privacy and robustness to adversarial examples
This short note highlights some links between two lines of research within the emerging topic of trustworthy machine learning: differential privacy and robustness to adversarial examples.
NGO-GM: Natural Gradient Optimization for Graphical Models
This paper deals with estimating model parameters in graphical models.
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.
Theoretical evidence for adversarial robustness through randomization
This paper investigates the theory of robustness against adversarial attacks.
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.
A discrete version of CMA-ES
This allows creating a version of CMA ES that can accommodate efficiently discrete variables.
Training compact deep learning models for video classification using circulant matrices
In real world scenarios, model accuracy is hardly the only factor to consider.
Uplift Modeling from Separate Labels
Uplift modeling is aimed at estimating the incremental impact of an action on an individual's behavior, which is useful in various application domains such as targeted marketing (advertisement campaigns) and personalized medicine (medical treatments).
Graph-based Clustering under Differential Privacy
In this paper, we present the first differentially private clustering method for arbitrary-shaped node clusters in a graph.
Explanatory relations in arbitrary logics based on satisfaction systems, cutting and retraction
The aim of this paper is to introduce a new framework for defining abductive reasoning operators based on a notion of retraction in arbitrary logics defined as satisfaction systems.
On the Needs for Rotations in Hypercubic Quantization Hashing
The aim of this paper is to endow the well-known family of hypercubic quantization hashing methods with theoretical guarantees.
Streaming Binary Sketching based on Subspace Tracking and Diagonal Uniformization
We demonstrate the quality of our binary sketches through experiments on real data for the nearest neighbors search task in the online setting.
Graph sketching-based Space-efficient Data Clustering
In this paper, we address the problem of recovering arbitrary-shaped data clusters from datasets while facing \emph{high space constraints}, as this is for instance the case in many real-world applications when analysis algorithms are directly deployed on resources-limited mobile devices collecting the data.
Structured adaptive and random spinners for fast machine learning computations
We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy.
Multi-dimensional signal approximation with sparse structured priors using split Bregman iterations
This paper addresses the structurally-constrained sparse decomposition of multi-dimensional signals onto overcomplete families of vectors, called dictionaries.
TripleSpin - a generic compact paradigm for fast machine learning computations
In particular, as a byproduct of the presented techniques and by using relatively new Berry-Esseen-type CLT for random vectors, we give the first theoretical guarantees for one of the most efficient existing LSH algorithms based on the $\textbf{HD}_{3}\textbf{HD}_{2}\textbf{HD}_{1}$ structured matrix ("Practical and Optimal LSH for Angular Distance").
Relaxation-based revision operators in description logics
In this paper we address both the generalization of the well-known AGM postulates, and the definition of concrete and well-founded revision operators in different DL families.
Belief Revision, Minimal Change and Relaxation: A General Framework based on Satisfaction Systems, and Applications to Description Logics
Belief revision of knowledge bases represented by a set of sentences in a given logic has been extensively studied but for specific logics, mainly propositional, and also recently Horn and description logics.
On the need for metrics in dictionary learning assessment
Dictionary-based approaches are the focus of a growing attention in the signal processing community, often achieving state of the art results in several application fields.
Subspace metrics for multivariate dictionaries and application to EEG
Overcomplete representations and dictionary learning algorithms are attracting a growing interest in the machine learning community.
Multi-dimensional sparse structured signal approximation using split Bregman iterations
An extensive empirical evaluation shows how the proposed approach compares to the state of the art depending on the signal features.
Metrics for Multivariate Dictionaries
Despite a recurrent need to rely on a distance for learning or assessing multivariate overcomplete representations, no metrics in their underlying spaces have yet been proposed.
