Minimax Statistical Learning with Wasserstein distances
Authors: Jaeho Lee, Maxim Raginsky
NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this work, we describe a minimax framework for statistical learning with ambiguity sets given by balls in Wasserstein space. In particular, we prove generalization bounds that involve the covering number properties of the original ERM problem. As an illustrative example, we provide generalization guarantees for transport-based domain adaptation problems where the Wasserstein distance between the source and target domain distributions can be reliably estimated from unlabeled samples. All proofs are deferred to the appendix. |
| Researcher Affiliation | Academia | Jaeho Lee Maxim Raginsky {jlee620, maxim}@illinois.edu Department of Electrical and Computer Engineering and Coordinated Science Laboratory, University of Illinois, Urbana, IL 61801, USA. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement about making its source code available or include a link to a code repository. |
| Open Datasets | No | The paper primarily deals with theoretical derivations and does not refer to specific public datasets with access information (URL, DOI, citation). It mentions 'n-tuple Z1, . . . , Zn of i.i.d. training examples' as a theoretical concept. |
| Dataset Splits | No | The paper does not specify dataset splits (e.g., train/validation/test percentages or sample counts) as it focuses on theoretical bounds rather than empirical evaluation. |
| Hardware Specification | No | The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory, or cloud instance types) used for running experiments, as it is a theoretical work. |
| Software Dependencies | No | The paper does not mention any specific software dependencies with version numbers (e.g., programming languages, libraries, or solvers). |
| Experiment Setup | No | The paper is theoretical and does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings. |