SIERRA - 2017 - Annual activity report

SIERRA

SIERRA - 2017

Project-Team Sierra

Personnel

Overall Objectives

Statement

Research Program

Supervised Learning
Unsupervised Learning
Parsimony
Optimization

Application Domains

Application Domains

New Software and Platforms

ProxASAGA
object-states-action

New Results

On Structured Prediction Theory with Calibrated Convex Surrogate Losses
Domain-Adversarial Training of Neural Networks
Linearly Convergent Randomized Iterative Methods for Computing the Pseudoinverse
Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance
Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization
Bridging the Gap between Constant Step Size Stochastic Gradient Descent and Markov Chains
AdaBatch: Efficient Gradient Aggregation Rules for Sequential and Parallel Stochastic Gradient Methods
Structure-Adaptive, Variance-Reduced, and Accelerated Stochastic Optimization
Exponential convergence of testing error for stochastic gradient methods
Optimal algorithms for smooth and strongly convex distributed optimization in networks
Stochastic Composite Least-Squares Regression with convergence rate O(1/n)
Sharpness, Restart and Acceleration
PAC-Bayes and Domain Adaptation
Kernel Square-Loss Exemplar Machines for Image Retrieval
Breaking the Nonsmooth Barrier: A Scalable Parallel Method for Composite Optimization
PAC-Bayesian Analysis for a two-step Hierarchical Multiview Learning Approach
Integration Methods and Accelerated Optimization Algorithms
GANs for Biological Image Synthesis
Nonlinear Acceleration of Stochastic Algorithms
Algorithmic Chaining and the Role of Partial Feedback in Online Nonparametric Learning
Frank-Wolfe Algorithms for Saddle Point Problems
Convex optimization over intersection of simple sets: improved convergence rate guarantees via an exact penalty approach
A Generic Approach for Escaping Saddle points
Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods
Combinatorial Penalties: Which structures are preserved by convex relaxations?
On the Consistency of Ordinal Regression Methods
Iterative hard clustering of features
Asaga: Asynchronous Parallel Saga
Sparse Accelerated Exponential Weights

Bilateral Contracts and Grants with Industry

Bilateral Contracts with Industry
Bilateral Grants with Industry

Partnerships and Cooperations

National Initiatives
European Initiatives
International Initiatives
International Research Visitors

Dissemination

Promoting Scientific Activities
Teaching - Supervision - Juries
Popularization

Bibliography

Publications of the year

Previous |

Home | Next next

Section: Research Program

Supervised Learning

This part of our research focuses on methods where, given a set of examples of input/output pairs, the goal is to predict the output for a new input, with research on kernel methods, calibration methods, and multi-task learning.

Previous |

Home | Next next