保証付き同変推論のための表現学習
Representation Learning for Equivariant Inference with Guarantees
物理や幾何の対称性を活かし、回帰・条件付き確率推定・不確かさ定量化を同時に行う同変表現学習フレームワークを提案し、非漸近的な統計的学習保証を与えた。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Daniel Ordoñez-Apraez, Vladimir Kostić, Alek Fröhlich, Vivien Brandt, Karim Lounici, Massimiliano Pontil
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
In many real-world applications of regression, conditional probability estimation, and uncertainty quantification, exploiting symmetries rooted in physics or geometry can dramatically improve generalization and sample efficiency. While geometric deep learning has made empirical advances by incorporating symmetry and geometry priors, less attention has been given to statistical learning guarantees. In this paper, we introduce an equivariant representation learning framework that simultaneously addresses regression, conditional probability estimation, and uncertainty quantification while providing first-of-its-kind non-asymptotic statistical learning guarantees. Grounded in operator and group representation theory, our framework approximates the spectral decomposition of the conditional expectation operator, building representations that are both equivariant and disentangled along independent symmetry quotient groups. Empirical evaluations on synthetic datasets and real-world robotics applications confirm the potential of our approach, matching or outperforming existing equivariant baselines in regression while providing well-calibrated uncertainty estimates.
