Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Online Prediction with Limited Selectivity
Authors: Licheng Liu, Mingda Qiao
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We introduce a theoretical model of Prediction with Limited Selectivity (PLS), which generalizes the selective prediction models of [Dru13, QV19]. We define a complexity measure termed approximate uniformity , which gives instance-dependent bounds on the optimal error that a forecasting algorithm can achieve on a PLS instance. For PLS instances that are randomly generated according to a k-monotone sequence (Definition 4), we show that the instance-dependent bounds match up to a constant factor with high probability. |
| Researcher Affiliation | Academia | Licheng Liu Imperial College London EMAIL Mingda Qiao University of Massachusetts Amherst EMAIL |
| Pseudocode | Yes | Algorithm 1: Random Select(s, k) Input: Integers s, k 1. Output: A pair (i, j) such that s i j and i + j s + 2k. 1 With probability 1/k, return (s + 2k 1, 2k 1); 2 p P2k 1 1 i=0 ls+i / P2k 1 i=0 ls+i ; 3 return Random Select(s, k 1) with probability p, and Random Select(s + 2k 1, k 1) with the remaining probability 1 p; Algorithm 2: Prediction with Limited Selectivity on Approximately Uniform Blocks Input: Instance L = (l1, l2, . . . , lm). Sequential access to sequence x [0, 1]n of length n = l1 + l2 + + lm. |
| Open Source Code | No | The answer NA means that paper does not include experiments requiring code. Please see the Neur IPS code and data submission guidelines (https://nips.cc/ public/guides/Code Submission Policy) for more details. While we encourage the release of code and data, we understand that this might not be possible, so No is an acceptable answer. Papers cannot be rejected simply for not including code, unless this is central to the contribution (e.g., for a new open-source benchmark). |
| Open Datasets | No | The answer NA means that the paper does not include experiments. |
| Dataset Splits | No | The answer NA means that the paper does not include experiments. |
| Hardware Specification | No | The answer NA means that the paper does not include experiments. |
| Software Dependencies | No | The answer NA means that the paper does not include experiments. |
| Experiment Setup | No | The answer NA means that the paper does not include experiments. |