paper-with-me

Papers

Optimization from Structured Samples for Coverage Functions

2020-07-06 · ICML 2020 1 · Wei Chen, Xiaoming Sun, Jialin Zhang, Zhijie Zhang

We revisit the optimization from samples (OPS) model, which studies the problem of optimizing objective functions directly from the sample data. Previous results showed that we cannot obtain a constant approximation ratio for the maximum coverage problem using polynomially many independent samples of the form $\{S_i, f(S_i)\}_{i=1}^t$ (Balkanski et al., 2017), even if coverage functions are $(1 - \epsilon)$-PMAC learnable using these samples (Badanidiyuru et al., 2012), which means most of the function values can be approximately learned very well with high probability. In this work, to circumvent the impossibility result of OPS, we propose a stronger model called optimization from structured samples (OPSS) for coverage functions, where the data samples encode the structural information of the functions. We show that under three general assumptions on the sample distributions, we can design efficient OPSS algorithms that achieve a constant approximation for the maximum coverage problem. We further prove a constant lower bound under these assumptions, which is tight when not considering computational efficiency. Moreover, we also show that if we remove any one of the three assumptions, OPSS for the maximum coverage problem has no constant approximation.

📄 PDF Abstract BibTeX arXiv:2007.02738

Code (0)

등록된 구현이 없습니다.

Tasks

Computational Efficiency

Similar Papers 제목 키워드 기반

The Limitations of Optimization from Samples

2015-12-19 · Eric Balkanski, Aviad Rubinstein, Yaron Singer

In this paper we consider the following question: can we optimize objective functions from the training data we use to learn them? We formalize this question through a novel framework we call optimization from samples (O…

In2Core: Leveraging Influence Functions for Coreset Selection in Instruction Finetuning of Large Language Models

2024-08-07 · Ayrton San Joaquin, Bin Wang, Zhengyuan Liu, Nicholas Asher 외

Despite advancements, fine-tuning Large Language Models (LLMs) remains costly due to the extensive parameter count and substantial data requirements for model generalization. Accessibility to computing resources remains …

Shape-Adaptive Conditional Calibration for Conformal Prediction via Minimax Optimization

2026-03-24 · Yajie Bao, Chuchen Zhang, Zhaojun Wang, Haojie Ren 외 arxiv

Achieving valid conditional coverage in conformal prediction is challenging due to the theoretical difficulty of satisfying pointwise constraints in finite samples. Building upon the characterization of conditional cover…

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage

2023-02-05 · NeurIPS 2023 11

In offline reinforcement learning (RL) we have no opportunity to explore so we must make assumptions that the data is sufficient to guide picking a good policy, taking the form of assuming some coverage, realizability, B…

Offline RLQ-LearningReinforcement Learning (RL)

Coverage and Capacity Optimization in STAR-RISs Assisted Networks: A Machine Learning Approach

2022-04-13 · Xinyu Gao, Wenqiang Yi, Alexandros Agapitos, Hao Wang 외

Coverage and capacity are the important metrics for performance evaluation in wireless networks, while the coverage and capacity have several conflicting relationships, e.g. high transmit power contributes to large cover…

BIG-bench Machine Learning