6 papers from the Criteo AI Lab at ICML 21:
- Online A-Optimal Design and Active Linear Regression, X. Fontaine (ENS Paris), P. Perrault (ENS Paris), V. Perchet (Criteo AI Lab / ENSAE), M. Valko (Deepmind)
- Pure Exploration and Regret Minimization in Matching Bandits, F. Sentenac (ENSAE), J. Yi (London School of Economics), C. Calauzènes (Criteo AI Lab), V. Perchet (Criteo AI Lab / ENSAE), M. Vojnovic (London School of Economics)
- Zeroth-Order Non-Convex Learning via Hierarchical Dual Averaging, P. Mertikopoulos (Criteo AI Lab / CNRS), A. Heliou (Criteo AI Lab), M. Martin (Criteo AI Lab), T. Rahier (Criteo AI Lab)
- The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets, Y. P. Hsieh (ETHZ) and V. Cevher (EPFL), P. Mertikopoulos (Criteo AI Lab / CNRS) [long talk]
- Regret Minimization in Stochastic Non-Convex Learning via a Proximal-Gradient Approach, N. Hallak (Technion) and V. Cevher (EPFL), P. Mertikopoulos (Criteo AI Lab / CNRS)
- Differentially-Private Sliced Wasserstein Distance, A. Rakotomamonjy (Criteo AI Lab), L. Ralaivola (Criteo AI Lab) [long talk]