Research map / Bandits and online learning / Online convex optimization and games
Online Learning with Transductive Regret
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Replace Blum and Mansour's fixed-point computation with reduced power method iterations (FASTSWAP) for swap regret | swap regret algorithm (FASTSWAP) · synthetic experiments, n in {40,...,200} weighted-majority base learners, 10,000 rounds | maximum number of RPM iterations (tau) needed | Helped |
| Use FASTSWAP per-iteration complexity O(N^2 log T) instead of O(N^3) fixed-point solve, under the minimal-probability assumption | swap regret algorithm (FASTSWAP) · theoretical complexity vs Blum and Mansour (2007) | per-iteration complexity | Helped |
| Extend time-selection swap regret algorithm to FASTTIMESELECTTRANSDUCE with per-round cost O(N^2 min{...}+|I|) instead of O(|I| N^N) | time-selection swap regret (Khot and Ponnuswami 2008 setting) · theoretical complexity | per-iteration complexity | Helped |
Closest papers by meaning
- Online Classification with Predictions (NeurIPS 2024 · similarity 0.88)
- Non-stationary Projection-Free Online Learning with Dynamic and Adaptive Regret Guarantees (AAAI 2024 · similarity 0.88)
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.88)
- Sequential Probability Assignment with Contexts: Minimax Regret, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood (NeurIPS 2024 · similarity 0.87)
- Online Learning with Unknown Constraints (ICML 2025 · similarity 0.87)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.