Pith. sign in

Spectral Representation Learning for Conditional Moment Models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

Many problems in causal inference and economics can be formulated in the framework of conditional moment models, which characterize the target function through a collection of conditional moment restrictions. For nonparametric conditional moment models, efficient estimation often relies on preimposed conditions on various measures of ill-posedness of the hypothesis space, which are hard to validate when flexible models are used. In this work, we address this issue by proposing a procedure that automatically learns representations with controlled measures of ill-posedness. Our method approximates a linear representation defined by the spectral decomposition of a conditional expectation operator, which can be used for kernelized estimators and is known to facilitate minimax optimal estimation in certain settings. We show this representation can be efficiently estimated from data, and establish L2 consistency for the resulting estimator. We evaluate the proposed method on proximal causal inference tasks, exhibiting promising performance on high-dimensional, semi-synthetic data.

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

background 1

representative citing papers

Representation Learning for Equivariant Inference with Guarantees

cs.LG · 2025-05-26 · conditional · novelty 6.0

An equivariant representation learning framework estimates conditional distributions through a block-diagonal conditional expectation operator, with non-asymptotic sample-complexity guarantees that improve with the symmetry group's structure.

citing papers explorer

Showing 1 of 1 citing paper.

  • Representation Learning for Equivariant Inference with Guarantees cs.LG · 2025-05-26 · conditional · none · ref 76 · internal anchor

    An equivariant representation learning framework estimates conditional distributions through a block-diagonal conditional expectation operator, with non-asymptotic sample-complexity guarantees that improve with the symmetry group's structure.