mlsanityData to 14 Oct 2026

Finite-Time 4-Expert Prediction Problem

arXiv 1911.10936 ↗First posted 22 Nov 2019math.PR cs.GT cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

We explicitly solve the nonlinear PDE that is the continuous limit of dynamic programming of expert prediction problem in finite horizon setting with N=4 experts. The expert prediction problem is formulated as a zero sum game between a player and an adversary. By showing that the solution is C2, we are able to show that the strategies conjectured in arXiv:1409.3040G form an asymptotic Nash equilibrium. We also prove the "Finite vs Geometric regret" conjecture proposed in arXiv:1409.3040G for N=4, and and show that this conjecture in fact follows from the conjecture that the comb strategies are optimal.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 7; 2023: 2; 2024: 1; 2025: 0; 2026: 4.

14 papers.

Sort:

  1. 2022PDE-Based Optimal Strategy for Unconstrained Online Learningcited by 27
  2. 2023Unconstrained Dynamic Regret via Sparse Codingcited by 11
  3. 2022Optimal Comparator Adaptive Online Learning with Switching Costcited by 9
  4. 2023Improving Adaptive Online Learning Using Refined Discretizationcited by 8
  5. 2022Continuous Prediction with Experts' Advicecited by 7
  6. 2022Efficient and Optimal Fixed-Time Regret with Two Expertscited by 5
  7. 2022A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Banditcited by 3
  8. 2024Numerical solution of a PDE arising from prediction with expert advicecited by 3
  9. 2026An explicit solution of the five-expert prediction PDE and the exact optimality set of COMBcited by 3
  10. 2022A New Approach to Drifting Games, Based on Asymptotically Optimal Potentialscited by 2
  11. 2026Prediction with Expert Advice: Anytime Regret with Many Experts Matches the Fixed-Time Constantcited by 2
  12. 2022A PDE approach for regret bounds under partial monitoringcited by 0
2 more
  1. 2026Operationalizing Stein's Method for Online Linear Optimization: CLT-Based Optimal Tradeoffscited by 0
  2. 2026On prediction from expert advice with more than five expertscited by 0