Optimization
Initializing Services in Interactive ML Systems for Diverse Users
This paper investigates ML systems serving a group of users, with multiple models/services, each aimed at specializing to a sub-group of users.
DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework
In contrast, in non-private settings, practitioners commonly utilize "adaptive" hyperparameter optimization methods such as Gaussian process-based optimization, which select the next candidate based on information gathered from previous outputs. This substantial contrast between private and non-private hyperparameter optimization underscores a critical concern. In our paper, we introduce DP-HyPO, a pioneering framework for "adaptive"
Functionally Constrained Algorithm Solves Convex Simple Bilevel Problems
Then we follow recent works to pursue the weak approximate solutions.
No-Regret M-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
Taihei Oki, Hokkaido University, Hokkaido, Japan, oki@icredd.hokudai.ac.jp "3026 Shinsaku Sakaue[1], The University of Tokyo and RIKEN AIP, Tokyo, Japan, sakaue@mist.i.u-tokyo.ac.jp
Below are details of our results.
title
For instance, data augmentation consistency regularization [Sohn et al., 2020, Berthelot et al., 2019] generates pseudo-labels from the current model predictions on
