I’m a postdoctoral fellow at KAUST, Saudi Arabia, hosted by Peter Richtárik. I did my PhD at Telecom Paris and Paris–Saclay University, France, under the supervision of Pascal Bianchi and Walid Hachem in the S2A (Signal, Statistics and Learning) team.
I use optimization, statistics, optimal transport, convex analysis etc. to study machine learning algorithms. I received the Masters degrees in 2015 from ENSAE Paris, where I studied statistics, and from Paris–Saclay University, where I studied probability theory. Here is my CV.
News
-
Next Fall (2021), I will be at UC Berkeley, USA, as a postdoctoral researcher of the Foundations of Data Science Institute and a Simons-Berkeley research fellow (for the program Geometric Methods in Optimization and Sampling).
-
I am presenting at NeurIPS 2020. The optimization paper in the Poster Session 3 and the sampling papers in the Poster Session 6.
-
The sessions I am co-organizing at SIAM Conference on Optimization 2020 are postponed until further notice, due to Covid19 outbreak. I am co-organizing the mini-symposium “Gradient flows and interactions between optimization and sampling algorithms” (Part I and Part II) with Anna Korba and the mini-symposium “Recent advances in primal-dual splitting for convex optimization” with Laurent Condat.
-
I gave a talk at the Second Symposium on Machine Learning and Dynamical Systems which was held virtually at the Fields Institute, Toronto. My pre-recorded talk on Langevin algorithm can be found here, and Anna’s talk on the MMD gradient flow is here.
Selected papers
Sampling and optimal transport
-
Anna Korba, Adil Salim, Michael Arbel, Giulia Luise and Arthur Gretton, “A Non-Asymptotic Analysis for Stein Variational Gradient Descent”, NeurIPS 2020.
-
Adil Salim and Peter Richtárik, “Primal Dual Interpretation of the Proximal Stochastic Gradient Langevin Algorithm”, NeurIPS 2020.
-
Adil Salim, Anna Korba and Giulia Luise, “The Wasserstein Proximal Gradient Algorithm”, NeurIPS 2020.
-
Adil Salim, Dmitry Kovalev and Peter Richtárik, “Stochastic Proximal Langevin Algorithm: Potential Splitting and Nonasymptotic Rates”, Spotlight @ NeurIPS 2019, Vancouver, Canada.
-
Michael Arbel, Anna Korba, Adil Salim and Arthur Gretton, “Maximum Mean Discrepancy Gradient Flow”, NeurIPS 2019, Vancouver, Canada.
Optimization and monotone operators
-
Dmitry Kovalev, Adil Salim and Peter Richtárik, “Optimal and Practical Algorithms for Smooth and Strongly Convex Decentralized Optimization”, NeurIPS 2020.
-
Adil Salim, Laurent Condat, Konstantin Mishchenko and Peter Richtárik, “Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms”, NeurIPS 2020 Workshop OPT2020: Optimization for Machine Learning.
-
Adil Salim, A Strong Law of Large Numbers for Random Monotone Operators, October 2019.
-
Pascal Bianchi, Walid Hachem and Adil Salim, A Fully Stochastic Primal-Dual Algorithm, Optimization Letters, June 2020.
-
Adil Salim, Pascal Bianchi, and Walid Hachem, “A Constant Step Stochastic Douglas-Rachford Algorithm with Application to Non Separable Regularization”, IEEE ICASSP 2018, Calgary, Canada.
-
Pascal Bianchi, Walid Hachem, and Adil Salim, Constant Step Stochastic Approximations Involving Differential Inclusions: Stability, Long-Run Convergence and Applications, Stochastics, May 2018.
-
Adil Salim, Pascal Bianchi, and Walid Hachem, Snake: a Stochastic Proximal Gradient Algorithm for Regularized Problems over Large Graphs, Transaction on Automatic Control, March 2018.
-
Pascal Bianchi, Walid Hachem, and Adil Salim, A constant step Forward-Backward algorithm involving random maximal monotone operators, Journal of Convex Analysis, March 2018.