Search Results for author:
Found 69 papers, 33 papers with code
Spectral Differential Network Analysis for High-Dimensional Time Series
Spectral networks derived from multivariate time series data arise in many domains, from brain science to Earth science.
StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task.
The Benefits of Balance: From Information Projections to Variance Reduction
Data balancing across multiple modalities and sources appears in various forms in foundation models in machine learning and AI, e. g. in CLIP and DINO.
From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models
One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results.
Iterated Schrödinger bridge approximation to Wasserstein Gradient Flows
We introduce a novel discretization scheme for Wasserstein gradient flows that involves successively computing Schr\"{o}dinger bridges with the same marginals.
Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
We consider the penalized distributionally robust optimization (DRO) problem with a closed, convex uncertainty set, a setting that encompasses learning using $f$-DRO and spectral/$L$-risk minimization.
JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of online authorship when needed, e. g., blind reviews for scientific papers, anonymous online reviews, or anonymous interactions in the mental health forums.
Distributionally Robust Optimization with Bias and Variance Reduction
We consider the distributionally robust optimization (DRO) problem with spectral risk-based uncertainty set and $f$-divergence penalty.
FiLM: Fill-in Language Models for Any-Order Generation
Language models have become the backbone of today's AI systems.
Faith and Fate: Limits of Transformers on Compositionality
We formulate compositional tasks as computation graphs to systematically quantify the level of complexity, and break down reasoning steps into intermediate sub-procedures.
Modified Gauss-Newton Algorithms under Noise
Gauss-Newton methods and their stochastic version have been widely used in machine learning and signal processing.
Confidence Sets under Generalized Self-Concordance
This paper revisits a fundamental problem in statistical inference from a non-asymptotic theoretical viewpoint $\unicode{x2013}$ the construction of confidence sets.
MAUVE Scores for Generative Models: Theory and Practice
We present MAUVE, a family of comparison measures between pairs of distributions such as those encountered in the generative modeling of text or images.
Stochastic Optimization for Spectral Risk Measures
Spectral risk objectives - also called $L$-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task.
Statistical and Computational Guarantees for Influence Diagnostics
Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications.
Stochastic optimization on matrices and a graphon McKean-Vlasov limit
We consider stochastic gradient descents on the space of large symmetric matrices of suitable functions that are invariant under permuting the rows and columns using the same permutation.
Iterative Linear Quadratic Optimization for Nonlinear Control: Differentiable Programming Algorithmic Templates
We present the implementation of nonlinear control algorithms based on linear and quadratic approximations of the objective from a functional viewpoint.
Orthogonal Statistical Learning with Self-Concordant Loss
Orthogonal statistical learning and double machine learning have emerged as general frameworks for two-stage statistical prediction in the presence of a nuisance component.
Flat minima generalize for low-rank matrix recovery
Empirical evidence suggests that for a variety of overparameterized nonlinear models, most notably in neural network training, the growth of the loss around a minimizer strongly impacts its performance.
Triangular Flows for Generative Modeling: Statistical Consistency, Smoothness Classes, and Fast Rates
Triangular flows, also known as Kn\"{o}the-Rosenblatt measure couplings, comprise an important building block of normalizing flow models for generative modeling and density estimation, including popular autoregressive flow models such as real-valued non-volume preserving transformation models (Real NVP).
Entropy Regularized Optimal Transport Independence Criterion
We introduce an independence criterion based on entropy regularized optimal transport.
Federated Learning with Superquantile Aggregation for Heterogeneous Data
We present a federated learning framework that is designed to robustly deliver good predictive performance across individual clients with heterogeneous data.
Target Propagation via Regularized Inversion
Target Propagation (TP) algorithms compute targets instead of gradients along neural networks and propagate them backward in a way that is similar yet different than gradient back-propagation (BP).
Stochastic Optimization under Distributional Drift
We consider the problem of minimizing a convex function that is evolving according to unknown and possibly stochastic dynamics, which may depend jointly on time and on the decision variable itself.
Score-Based Change Detection for Gradient-Based Learning Machines
The widespread use of machine learning algorithms calls for automatic change detection algorithms to monitor their behavior over time.
Divergence Frontiers for Generative Models: Sample Complexity, Quantization Effects, and Frontier Integrals
The spectacular success of deep generative models calls for quantitative tools to measure their statistical performance.
Stochastic optimization under time drift: iterate averaging, step-decay schedules, and high probability guarantees
We consider the problem of minimizing a convex function that is evolving in time according to unknown and possibly stochastic dynamics.
MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers
As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem.
Differentiable Programming à la Moreau
The notion of a Moreau envelope is central to the analysis of first-order optimization algorithms for machine learning.
Faster Policy Learning with Continuous-Time Gradients
We study the estimation of policy gradients for continuous-time systems with known dynamics.
Asymptotics of Discrete Schrödinger Bridges via Chaos Decomposition
We consider instead in this paper the problem where each matching is endowed with a Gibbs probability weight proportional to the exponential of the negative total cost of that matching.
First-order Optimization for Superquantile-based Supervised Learning
Classical supervised learning via empirical risk (or negative log-likelihood) minimization hinges upon the assumption that the testing distribution coincides with the training distribution.
Harmonic Decompositions of Convolutional Networks
We present a description of the function space and the smoothness class associated with a convolutional network using the machinery of reproducing kernel Hilbert spaces.
A Spectral Analysis of Dot-product Kernels
We present eigenvalue decay estimates of integral operators associated with compositional dot-product kernels.
Device Heterogeneity in Federated Learning: A Superquantile Approach
We propose a federated learning framework to handle heterogeneous client devices which do not conform to the population data distribution.
An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks
We present an approach to obtain convergence guarantees of optimization algorithms for deep networks based on elementary arguments and computations.
Robust Aggregation for Federated Learning
We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server.
Discriminative Clustering with Representation Learning with any Ratio of Labeled to Unlabeled Data
We present a discriminative clustering approach in which the feature representation can be learned from data and moreover leverage labeled data.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
A Statistical Investigation of Long Memory in Language and Music
Representation and learning of long-range dependencies is a central challenge confronted in modern applications of machine learning to sequence data.
Kernel-based Translations of Convolutional Networks
Convolutional Neural Networks, as most artificial neural networks, are commonly viewed as methods different in essence from kernel-based methods.
A Smoother Way to Train Structured Prediction Models
We present a framework to train a structured prediction model by performing smoothing on the inference algorithm it builds upon.
Object Discovery in Videos as Foreground Motion Clustering
We consider the problem of providing dense segmentation masks for object discovery in videos.
Coupled Recurrent Models for Polyphonic Music Composition
This paper introduces a novel recurrent model for music composition that is tailored to the structure of polyphonic music.
Adaptive Denoising of Signals with Local Shift-Invariant Structure
We discuss the problem of adaptive discrete-time signal denoising in the situation where the signal to be recovered admits a "linear oracle" -- an unknown linear estimate that takes the form of convolution of observations with a time-invariant filter.
Efficient First-Order Algorithms for Adaptive Signal Denoising
Our second contribution is a computational complexity analysis of the proposed procedures, which takes into account their statistical nature and the related notion of statistical accuracy.
Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice
One of the keys to achieve acceleration in theory and in practice is to solve these sub-problems with appropriate accuracy by using the right stopping criterion and the right warm-start strategy.
Invariances and Data Augmentation for Supervised Music Transcription
This paper explores a variety of models for frame-based music transcription, with an emphasis on the methods needed to reach state-of-the-art on human recordings.
Catalyst Acceleration for Gradient-Based Non-Convex Optimization
We introduce a generic scheme to solve nonconvex optimization problems using gradient-based algorithms originally designed for minimizing convex functions.
Learning Features of Music from Scratch
This paper introduces a new large-scale music dataset, MusicNet, to serve as a source of supervision and evaluation of machine learning methods for music research.
Ranked #6 on
Music Transcription
on MusicNet
An Inexact Variable Metric Proximal Point Algorithm for Generic Quasi-Newton Acceleration
We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms.
Fast and Simple Optimization for Poisson Likelihood Models
Since almost all gradient-based optimization algorithms rely on Lipschitz-continuity, optimizing Poisson likelihood models with a guarantee of convergence can be challenging, especially for large-scale problems.
Structure-Blind Signal Recovery
We consider the problem of recovering a signal observed in Gaussian noise.
Statistics Theory Statistics Theory
Rademacher Complexity Bounds for a Penalized Multiclass Semi-Supervised Algorithm
We propose Rademacher complexity bounds for multiclass classifiers trained with a two-step semi-supervised model.
Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach
Convolutional neural networks (CNNs) have recently received a lot of attention due to their ability to model local stationary structures in natural images in a multi-scale fashion, when learning all model parameters with supervision.
Local Convolutional Features With Unsupervised Training for Image Retrieval
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval.
Beat-Event Detection in Action Movie Franchises
While important advances were recently made towards temporally localizing and recognizing specific human actions or activities in videos, efficient detection and classification of long video chunks belonging to semantically defined categories such as "pursuit" or "romance" remains challenging. We introduce a new dataset, Action Movie Franchises, consisting of a collection of Hollywood action movie franchises.
Semi-proximal Mirror-Prox for Nonsmooth Composite Minimization
We propose a new first-order optimisation algorithm to solve high-dimensional non-smooth composite minimisation problems.
DeepMatching: Hierarchical Deformable Dense Matching
We introduce a novel matching algorithm, called DeepMatching, to compute dense correspondences between images.
Ranked #4 on
Dense Pixel Correspondence Estimation
on HPatches
Dense Pixel Correspondence Estimation
Optical Flow Estimation
Learning to track for spatio-temporal action localization
We present experimental results for spatio-temporal localization on the UCF-Sports, J-HMDB and UCF-101 action localization datasets, where our approach outperforms the state of the art with a margin of 15%, 7% and 12% respectively in mAP.
Spatio-Temporal Action Localization
Temporal Action Localization
+1
Learning to Detect Motion Boundaries
We compare the results obtained with several state-of-the-art optical flow approaches and study the impact of the different cues used in the random forest. Furthermore, we introduce a new dataset, the YouTube Motion Boundaries dataset (YMB), that comprises 60 sequences taken from real-world videos with manually annotated motion boundaries.
Label-Embedding for Image Classification
Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce.
Ranked #7 on
Multi-label zero-shot learning
on Open Images V4
EpicFlow: Edge-Preserving Interpolation of Correspondences for Optical Flow
We propose a novel approach for optical flow estimation , targeted at large displacements with significant oc-clusions.
Convolutional Kernel Networks
An important goal in visual recognition is to devise image representations that are invariant to particular transformations.
Ranked #24 on
Image Classification
on MNIST
Transformation Pursuit for Image Classification
We propose a principled algorithm Image Transformation Pursuit (ITP) for the automatic selection of a compact set of transformations.
Fast and Robust Archetypal Analysis for Representation Learning
We revisit a pioneer unsupervised learning technique called archetypal analysis, which is related to successful data analysis methods such as sparse coding and non-negative matrix factorization.
On learning to localize objects with minimal supervision
Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain.
Ranked #41 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Label-Embedding for Attribute-Based Classification
The label embedding framework offers other advantages such as the ability to leverage alternative sources of information in addition to attributes (e. g. class hierarchies) or to transition smoothly from zero-shot learning to learning with large quantities of data.
Conditional Gradient Algorithms for Norm-Regularized Smooth Convex Optimization
Motivated by some applications in signal processing and machine learning, we consider two convex optimization problems where, given a cone $K$, a norm $\|\cdot\|$ and a smooth convex function $f$, we want either 1) to minimize the norm over the intersection of the cone and a level set of $f$, or 2) to minimize over the cone the sum of $f$ and a multiple of the norm.
