This paper considers a multi-environment factor model in which high-dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subset of these environments. The joint distribution of the covariates may vary across environments, whereas the latent structure is decomposed into invariant factors with shared loadings and heterogeneous factors with environment-specific loadings.
arXiv:2607. 18209v1 Announce Type: cross Abstract: This paper considers a multi-environment factor model in which high-dimensional covariates are collected from heterogeneous environments, with auxiliary labels available in a subset of these environments.
arXiv:2608. 16245v1 Announce Type: new Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate.
The paper introduces a transfer learning framework for structured matrix estimation when both the ambient dimension and the intrinsic representation grow over time. It models the target parameter as an embedded source component plus low‑rank innovations and sparse edits, and proposes an anchored alternating projection estimator that preserves the transferred subspace while estimating only the new components. Deterministic error bounds are derived that separate target noise, representation growth, and source estimation error, showing improved rates when rank and sparsity increments are small, and the framework is applied to Markov transition matrix estimation and structured covariance estimation with theoretical guarantees and empirical validation.
arXiv:1811. 05336v2 Announce Type: replace-cross Abstract: Inference for factor models is often hampered by the lack of tractable and accurate variance estimates, which can materially distort downstream analyses.
arXiv:2608. 11917v1 Announce Type: new Abstract: Multi-output Gaussian process regression scales cubically in the number of observations times outputs, and dense kernel-matrix methods need bespoke handling whenever different outputs are observed at different inputs.
arXiv:2608. 20065v1 Announce Type: new Abstract: World models construct latent states that support prediction, planning, and reasoning about an underlying system.
arXiv:2607. 23337v1 Announce Type: new Abstract: Neural operators provide data-driven mappings for modeling dynamical systems.
Orthogonal JEPA introduces a latent world‑modeling framework that factorizes predictive states into orthogonal components. By learning basis matrices and dedicated prediction branches, the method reduces redundancy and improves gradient signals for less dominant predictive structures. The factorized states can be synthesized into complete latent representations for downstream tasks such as decoding, planning, or autoregressive rollout, and are evaluated across vision, biology, health, control, and molecular dynamics domains.
arXiv:2509. 09371v2 Announce Type: replace-cross Abstract: Distributionally robust optimization (DRO) protects statistical learning against distributional shifts by optimizing the worst-case performance over a set of perturbed distributions.
arXiv:2608. 09742v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) represents large language model (LLM) updates with two compact matrix factors, i.
arXiv:2609.24241v1 Announce Type: new Abstract: Uncovering latent variables and their causal relations from observed data is a fundamental yet challenging problem. Existing methods often rely on rest...
arXiv:2603. 27631v2 Announce Type: replace Abstract: Self-supervised pre-training, where large corpora of unlabeled data are used to learn representations for downstream fine-tuning, has become a cornerstone of modern machine learning.