<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Online Learning |</title><link>https://nick-jhlee.github.io/tags/online-learning/</link><atom:link href="https://nick-jhlee.github.io/tags/online-learning/index.xml" rel="self" type="application/rss+xml"/><description>Online Learning</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Thu, 21 May 2026 00:00:00 +0000</lastBuildDate><image><url>https://nick-jhlee.github.io/media/icon_hu_eee4a95885829ab2.png</url><title>Online Learning</title><link>https://nick-jhlee.github.io/tags/online-learning/</link></image><item><title>Looking Through the Mirror: Minimax-Optimal Regularized Regrets in Online Learning and Bandits</title><link>https://nick-jhlee.github.io/publications/arxiv26-regularized-regret/</link><pubDate>Thu, 21 May 2026 00:00:00 +0000</pubDate><guid>https://nick-jhlee.github.io/publications/arxiv26-regularized-regret/</guid><description/></item><item><title>A Jointly Efficient and Optimal Algorithm for Heteroskedastic Generalized Linear Bandits with Adversarial Corruptions</title><link>https://nick-jhlee.github.io/publications/arxiv26-corrupted-glm/</link><pubDate>Thu, 12 Feb 2026 00:00:00 +0000</pubDate><guid>https://nick-jhlee.github.io/publications/arxiv26-corrupted-glm/</guid><description/></item><item><title>Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion</title><link>https://nick-jhlee.github.io/publications/aistats24/</link><pubDate>Sat, 20 Jan 2024 00:00:00 +0000</pubDate><guid>https://nick-jhlee.github.io/publications/aistats24/</guid><description/></item></channel></rss>