In this paper, we propose a unified, efficient and modular approach for implicit differentiation of optimization problems.
Second, we show that inverting permutations is a meaningful pretext task for learning audio representations in an unsupervised fashion.
In particular, we also improve music understanding by reordering spectrogram patches in the frequency space, as well as video classification by reordering frames along the time axis.
Machine learning pipelines often rely on optimizers procedures to make discrete decisions (e. g., sorting, picking closest neighbors, or shortest paths).
Our goal in this paper is to propose new group testing algorithms that can operate in a noisy setting (tests can be mistaken) to decide adaptively (looking at past results) which groups to test next, with the goal to converge to a good detection, as quickly, and with as few tests as possible.
Machine learning pipelines often rely on optimization procedures to make discrete decisions (e. g., sorting, picking closest neighbors, or shortest paths).
While numerous works have proposed differentiable proxies to sorting and ranking, they do not achieve the $O(n \log n)$ time complexity one would expect from sorting and ranking operations.
We study the problem of hypothesis testing between two discrete distributions, where we only have access to samples after the action of a known reversible Markov chain, playing the role of noise.
We consider the problem of link prediction, based on partial observation of a large network, and on side information associated to its vertices.
We consider the problem of bandit optimization, inspired by stochastic optimization and online learning problems with bandit feedback.
We describe the properties of random instances of flat satisfiability, as well of the optimal rates of detection of the associated hypothesis testing problem.
In this paper, we show that, under a widely-believed assumption from computational complexity theory, there is a fundamental trade-off between statistical and computational performance in this problem.