Search Results for author:
Found 13 papers, 2 papers with code
Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm
The first algorithm uses a gradient estimator based on randomization over the $\ell_2$ sphere due to Bach and Perchet (2016).
Parameter-free projected gradient descent
We consider the problem of minimizing a convex function over a closed convex set, with Projected Gradient Descent (PGD).
SignSVRG: fixing SignSGD via variance reduction
The core idea is first instantiated on the problem of minimizing sums of convex and Lipschitz functions and is then extended to the smooth case via variance reduction.
Fair learning with Wasserstein barycenters for non-decomposable performance measures
In the awareness framework, akin to the classical unconstrained classification case, we show that maximizing accuracy under this fairness constraint is equivalent to solving a corresponding regression problem followed by thresholding at level $1/2$.
A gradient estimator via L1-randomization for online zero-order optimization with two point feedback
We present a novel gradient estimator based on two function evaluations and randomization on the $\ell_1$-sphere.
A Unified Approach to Fair Online Learning via Blackwell Approachability
We provide a setting and a general approach to fair online learning with stochastic sensitive and non-sensitive contexts.
Classification with abstention but without disparities
Building on this result, we propose a post-processing classification algorithm, which is able to modify any off-the-shelf score-based classifier using only unlabeled sample.
Set-valued classification -- overview via a unified framework
Multi-class classification problem is among the most popular and well-studied statistical frameworks.
Fair regression via plug-in estimator and recalibration with statistical guarantees
We study the problem of learning an optimal regression function subject to a fairness constraint.
An example of prediction which complies with Demographic Parity and equalizes group-wise risks in the context of regression
We provide a non-trivial example of a prediction $x \to f(x)$ which satisfies two common group-fairness notions: Demographic Parity \begin{align} (f(X) | S = 1) &\stackrel{d}{=} (f(X) | S = 2) \end{align} and Equal Group-Wise Risks \begin{align} \mathbb{E}[(f^*(X) - f(X))^2 | S = 1] = \mathbb{E}[(f^*(X) - f(X))^2 | S = 2].
Leveraging Labeled and Unlabeled Data for Consistent Fair Binary Classification
We study the problem of fair binary classification using the notion of Equal Opportunity.
On the benefits of output sparsity for multi-label classification
The modern multi-label problems are typically large-scale in terms of number of observations, features and labels, and the amount of labels can even be comparable with the amount of observations.
