No article text was recorded for this version.
unknown time horizon
Version 1 of 130 papers30 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Agnostic Smoothed Online Learning
- Blog: Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families
- Blog: Logistic Regression Regret: What's the Catch?
- Blog: A Simple yet Universal Strategy for Online Convex Optimization
- Blog: Multistage Knapsack
- Blog: Prediction by random-walk perturbation
- Blog: One-Point Sampling for Distributed Bandit Convex Optimization with Time-Varying Constraints
- Blog: An adaptive algorithm for finite stochastic partial monitoring
- Blog: Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints
- Blog: Decoupling Learning and Decision-Making: Breaking the O(T) Barrier in Online Resource Allocation with First-Order Methods
- Blog: Adaptive Algorithms for Online Convex Optimization with Long-term Constraints
- Blog: Exchangeability Characterizes Optimality of Sequential Normalized Maximum Likelihood and Bayesian Prediction with Jeffreys Prior
- Blog: Near-Optimal Rates for Limited-Delay Universal Lossy Source Coding
- Blog: Stochastic Online Metric Matching: Adversarial is no Harder than Stochastic
- Blog: Prediction strategies without loss
- Blog: Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models
- Blog: Second-order Quantile Methods for Experts and Combinatorial Games
- Blog: Strategies for Prediction Under Imperfect Monitoring
- Blog: Tight Bounds for Online Convex Optimization with Adversarial Constraints
- Blog: Efficient Minimax Strategies for Square Loss Games
- Blog: Minimax Optimal Algorithms for Unconstrained Linear Optimization
- Blog: Online Learning With Uncertain Feedback Graphs
- Blog: Coin Betting and Parameter-Free Online Learning
- Blog: Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
- Blog: Improved Algorithms for Online Submodular Maximization via First-order Regret Bounds
- Blog: Minimizing Dynamic Regret and Adaptive Regret Simultaneously
- Blog: A Simple yet Universal Strategy for Online Convex Optimization
- Blog: Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings
- Blog: Towards Minimax Online Learning with Unknown Time Horizon
- Blog: Simultaneously Achieving Sublinear Regret and Constraint Violations for Online Convex Optimization with Time-varying Constraints
History & citation
Current · Permanent link
- This direction split from Anytime Algorithms for Horizon Independent Online Learning (60% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_unknown_time_horizon_eadbdeff,
title = {unknown time horizon},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unknown-time-horizon/rdr_eadbdeffde224d8087d369a25b9e482c},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_unknown_time_horizon_eadbdeff_v1,
title = {unknown time horizon},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unknown-time-horizon/rdr_eadbdeffde224d8087d369a25b9e482c/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}