
Harmonic Decompositions of Convolutional Networks
We consider convolutional networks from a reproducing kernel Hilbert spa...
read it

Risk Bounds for Multilayer Perceptrons through Spectra of Integral Operators
We characterize the behavior of integral operators associated with multi...
read it

Device Heterogeneity in Federated Learning: A Superquantile Approach
We propose a federated learning framework to handle heterogeneous client...
read it

An Elementary Approach to Convergence Guarantees of Optimization Algorithms for Deep Networks
We present an approach to obtain convergence guarantees of optimization ...
read it

Robust Aggregation for Federated Learning
We present a robust aggregation approach to make federated learning robu...
read it

Endtoend Learning, with or without Labels
We present an approach for endtoend learning that allows one to jointl...
read it

Advances and Open Problems in Federated Learning
Federated learning (FL) is a machine learning setting where many clients...
read it

A Statistical Investigation of Long Memory in Language and Music
Representation and learning of longrange dependencies is a central chal...
read it

Kernelbased Translations of Convolutional Networks
Convolutional Neural Networks, as most artificial neural networks, are c...
read it

A Smoother Way to Train Structured Prediction Models
We present a framework to train a structured prediction model by perform...
read it

Object Discovery in Videos as Foreground Motion Clustering
We consider the problem of providing dense segmentation masks for object...
read it

Coupled Recurrent Models for Polyphonic Music Composition
This work describes a novel recurrent model for music composition, which...
read it

Adaptive Denoising of Signals with ShiftInvariant Structure
We study the problem of discretetime signal denoising, following the li...
read it

Efficient FirstOrder Algorithms for Adaptive Signal Denoising
We consider the problem of discretetime signal denoising, focusing on a...
read it

Catalyst Acceleration for Firstorder Convex Optimization: from Theory to Practice
We introduce a generic scheme for accelerating gradientbased optimizati...
read it

Invariances and Data Augmentation for Supervised Music Transcription
This paper explores a variety of models for framebased music transcript...
read it

Catalyst Acceleration for GradientBased NonConvex Optimization
We introduce a generic scheme to solve nonconvex optimization problems u...
read it

A Generic QuasiNewton Algorithm for Faster GradientBased Optimization
We propose a generic approach to accelerate gradientbased optimization ...
read it

Fast and Simple Optimization for Poisson Likelihood Models
Poisson likelihood models have been prevalently used in imaging, social ...
read it

Rademacher Complexity Bounds for a Penalized Multiclass SemiSupervised Algorithm
We propose Rademacher complexity bounds for multiclass classifiers train...
read it

Convolutional Patch Representations for Image Retrieval: an Unsupervised Approach
Convolutional neural networks (CNNs) have recently received a lot of att...
read it

DeepMatching: Hierarchical Deformable Dense Matching
We introduce a novel matching algorithm, called DeepMatching, to compute...
read it

Learning to track for spatiotemporal action localization
We propose an effective approach for spatiotemporal action localization...
read it

LabelEmbedding for Image Classification
Attributes act as intermediate representations that enable parameter sha...
read it

EpicFlow: EdgePreserving Interpolation of Correspondences for Optical Flow
We propose a novel approach for optical flow estimation , targeted at la...
read it

Convolutional Kernel Networks
An important goal in visual recognition is to devise image representatio...
read it

Fast and Robust Archetypal Analysis for Representation Learning
We revisit a pioneer unsupervised learning technique called archetypal a...
read it

Conditional Gradient Algorithms for NormRegularized Smooth Convex Optimization
Motivated by some applications in signal processing and machine learning...
read it

Testing for Homogeneity with Kernel Fisher Discriminant Analysis
We propose to investigate test statistics for testing homogeneity in rep...
read it
Zaid Harchaoui
is this you? claim profile
Provost’s Initiative in Datadriven Discovery, Assistant professor in the department of statistics at University of Washington, Ph.D. at ParisTech (now in Univ. ParisSaclay), visiting assistant professor at the Courant Institute for Mathematical Sciences at New York University (2015 – 2016), Permanent Researcher on the LEAR team of Inria (2010 – 2015). Postdoctoral Fellow in the Robotics Institute of Carnegie Mellon University in 2009, Inria award for scientific excellence and the NIPS reviewer award, Area Chair for ICML 2015, ICML 2016, NIPS 2016, ICLR 2016. He is currently an associate editor of IEEE Signal Processing Letters.