High-Dimensional Robust Statistics with Ilias Diakonikolas - #351

episode

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

Related

recent transcribed audio

MIDWEEK RUB | Should Lachie Neale Get Off? Full Grand Final Preview + Brownlow Wrap 38 min · 23 Sep 2026 · Triple M Rocks Footy AFL

NPR News: 09-22-2026 9PM EDT 4 min · 23 Sep 2026 · NPR News Now

9PM ET 09/22/2026 Newscast 3 min · 23 Sep 2026 · Fox News Hourly Update

Stories from our Elders: My passionate friendship with a rebel poet 51 min · 23 Sep 2026 · Conversations

The forgotten nutrient every midlife woman needs – with Dr Craig Rose 41 min · 23 Sep 2026 · Age Better with Liz Earle

Bringing Kashmir’s lakes back to life 25 min · 23 Sep 2026 · The Documentary Podcast

Report any issue

Source

Recorded24 Feb 2020

Publisherfeeds.megaphone.fm ↗

Handlerec:12496187

Show notes

Today we’re joined by Ilias Diakonikolas, faculty in the CS department at the University of Wisconsin-Madison, and author of the paper Distribution-Independent PAC Learning of Halfspaces with Massart Noise, recipient of the NeurIPS 2019 Outstanding Paper award. The paper is regarded as the first progress made around distribution-independent learning with noise since the 80s. In our conversation, we explore robustness in ML, problems with corrupt data in high-dimensional settings, and of course, the paper.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.

Sign in