mlsanityData to 14 Oct 2026

An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB

arXiv 2609.14892 ↗First posted 14 Sep 2026math.AP cs.GT cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, we derive an explicit solution of the stationary prediction with expert advice PDE for five experts. The formula is given in three regions. In the first two regions, it is the four-expert solution plus a single integral with an elementary positive density. In the third region, it is a finite sum of hyperbolic products whose coefficients are determined by one scalar quadrature. Our formula establishes that the direction (1,0,1,0,0) is optimal throughout the ordered sector, and that the COMB strategy (1,0,1,0,1) is optimal only on a lower dimensional subset of the sector (where x1=x2 and x3=x4). This disproves the COMB optimality conjecture of Gravin, Peres and Sivan. The verification of the Hamiltonian inequalities is a tedious task, part of which is completed with a computer assisted proof. The verification reduces to 21 scalar inequalities, which we prove using 147 exact rational Bernstein polynomial certificates. The exact certificates and their independent arithmetic checks are included in a supplement to this paper, and a Lean 4 formalization machine-checks the verification and both main theorems, apart from the viscosity characterization.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 36 references that are in the map. First posted on arXiv 14 Sep 2026.

Builds on

14 of 36 references.

References · 14

  1. 2019Prediction with Expert Advice: a PDE Perspectivecited by 17
  2. 2019New Potential-Based Bounds for Prediction with Expert Advicecited by 16
  3. 2019Finite-Time 4-Expert Prediction Problemcited by 14
  4. 2014Towards Optimal Algorithms for Prediction with Expert Advicecited by 13
  5. 2019On the asymptotic optimality of the comb strategy for prediction with expert advicecited by 10
  6. 2016Tight Lower Bounds for Multiplicative Weights Algorithmic Familiescited by 9
  7. 2020A PDE Approach to the Prediction of a Binary Sequence with Advice from Two History-Dependent Expertscited by 7
  8. 2013Towards Minimax Online Learning with Unknown Time Horizoncited by 6
  9. 2019Experimental Evidence for Asymptotic Non-Optimality of Comb Adversary Strategycited by 6
  10. 2019New Potential-Based Bounds for the Geometric-Stopping Version of Prediction with Expert Advicecited by 6
  11. 2020Malicious Experts versus the multiplicative weights algorithm in online predictioncited by 6
  12. 2020Online Prediction With History-Dependent Experts: The General Casecited by 6
2 more
  1. 2020Asymptotically optimal strategies for online prediction with history-dependent expertscited by 4
  2. 2024Numerical solution of a PDE arising from prediction with expert advicecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.