REVIEW 9 cited by
Domain Adaptation: Learning Bounds and Algorithms
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Domain Adaptation: Learning Bounds and Algorithms
read the original abstract
This paper addresses the general problem of domain adaptation which arises in a variety of applications where the distribution of the labeled sample available somewhat differs from that of the test data. Building on previous work by Ben-David et al. (2007), we introduce a novel distance between distributions, discrepancy distance, that is tailored to adaptation problems with arbitrary loss functions. We give Rademacher complexity bounds for estimating the discrepancy distance from finite samples for different loss functions. Using this distance, we derive novel generalization bounds for domain adaptation for a wide family of loss functions. We also present a series of novel adaptation bounds for large classes of regularization-based algorithms, including support vector machines and kernel ridge regression based on the empirical discrepancy. This motivates our analysis of the problem of minimizing the empirical discrepancy for various loss functions for which we also give novel algorithms. We report the results of preliminary experiments that demonstrate the benefits of our discrepancy minimization algorithms for domain adaptation.
Forward citations
Cited by 9 Pith papers
-
Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
SeqRejectron constructs a stopping rule with a small set of validator policies to achieve horizon-free sample complexity for selective imitation learning under arbitrary dynamics shifts.
-
Learning When to Stop: Selective Imitation Learning Under Arbitrary Dynamics Shift
SeqRejectron builds a stopping rule from a small set of validator policies to achieve horizon-free sample-complexity guarantees for selective imitation learning under arbitrary train-test dynamics shifts.
-
Adaptive Kernel Ridge Regression with Linear Structure: Sharp Oracle Inequalities and Minimax Optimality
An augmented kernel ridge regression estimator separates linear and nonlinear components to achieve sharp oracle inequalities and minimax optimal prediction risk under general kernels.
-
Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models
Three frameworks adapt foundation models for generalized category discovery under domain shifts via disentanglement and prompt tuning, showing gains on synthetic and real multi-domain data.
-
Transformers for dynamical systems learn transfer operators in-context
Small transformers learn to forecast unseen dynamical systems in-context by using delay embeddings to recover the manifold and forecasting its invariant sets via a transfer-operator strategy.
-
ACE and Diverse Generalization via Selective Disagreement
ACE learns an ensemble of classifiers that agree on labeled data but confidently and selectively disagree on target-distribution data, recovering diverse human-interpretable concepts under complete spurious correlation.
-
Quantifying Error in the Presence of Confounders for Causal Inference
Frames causal inference methods as representation learners to derive general and estimable error bounds, extending them to unobserved confounding via robust statistics.
-
Pitfalls of Unlabeled Disagreement-Based Drift Detection in Streaming Tree Ensembles
Disagreement measures from label flipping in IDT ensembles underperform loss-based drift detectors in streaming tabular data due to the limited plasticity of tree models.
-
From Weights to Activations: Is Steering the Next Frontier of Adaptation?
Steering is positioned as a distinct adaptation paradigm that uses targeted activation interventions for local, reversible behavioral changes without parameter updates.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.