Masashi Sugiyama

Machine Learning from Weak, Noisy, and Biased Supervision

Masashi Sugiyama, University of Tokyo and RIKEN

Abstract: In statistical inference and machine learning, we face a variety of uncertainties such as training data with insufficient information, label noise, and bias. In this talk, I will give an overview of our research on reliable machine learning, including weakly supervised classification (positive unlabeled classification, positive confidence classification, complementary label classification, etc.), noisy label classification (noise transition estimation, instance-dependent noise, clean sample selection, etc.), and transfer learning (joint importance-predictor estimation for covariate shift adaptation, dynamic importance estimation for full distribution shift, continuous distribution shift, etc.).

The event is finished.

Date

Sep 18 2023
Expired!

Time

10:00 AM - 11:00 AM

Local Time

  • Timezone: America/New_York
  • Date: Sep 18 2023
  • Time: 1:00 PM - 2:00 PM

Location

Virtual

Organizer

TILOS & OPTML++

Speaker