Extends covariance estimation with multiple targets for better performance.
problem Improving covariance estimation for multiple targets.
method Combines multiple constant matrices with sample covariance matrix, derives estimators and proves convergence.
result The multi-target linear shrinkage estimator outperforms other estimators in various situations.
MALT improves adversarial attacks by targeting classes more efficiently.
problem Naive targeting of adversarial attacks based on classifier confidence.
method MALT - Mesoscopic Almost Linearity Targeting, based on medium-scale almost linearity assumptions.
result MALT wins over AutoAttack on CIFAR-100 and ImageNet datasets, five times faster.
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
Paper proposes a method to learn linear regression models using multiple pre-trained models.
problem Learning a linear regression model with limited target data.
method Representation transfer learning method using multiple pre-trained models.
result The method achieves better sample complexity compared to baseline methods.
Paper proposes scalable algorithm to estimate intervention targets in linear models.
problem Estimating intervention targets in linear models from observational and interventional data.
method The paper proposes a scalable algorithm that estimates intervention sites from the difference between precision matrices of observational and interventional datasets.
result The algorithm consistently identifies all intervention targets and updates observational Markov equivalence classes to interventional ones.
We propose a new Bayesian tracking and parameter learning algorithm for non-linear non-Gaussian multiple target tracking (MTT) models. We design a Markov chain Monte Carlo (MCMC) algorithm to sample from the posterior distribution of the target states, birth and death times, and association of observations to targets, …
Study shows pretraining and finetuning can effectively tackle covariate shift in linear regression.
problem Linear regression under covariate shift where source and target distributions differ but conditional distribution remains similar.
method Pretraining on source data and finetuning on target data using online SGD.
result Transfer learning with O(N2) source data is as effective as supervised learning with N target data. We reveal a model rank that predicts successful recovery of target functions at overparameterization.
problem Understanding the mysterious good generalization performance of overparameterized nonlinear models.
method Rank stratification and linear stability theory for general nonlinear models.
result Linearly stable functions are preferred by nonlinear training, and model rank predicts minimal training data size.
Develops estimators for near-optimal linear regression under distribution shift.
problem Linear regression under distribution shift with scarce target domain data.
method Minimax linear risk estimators covering various transfer learning settings.
result Achieves near-optimal risk for linear regression problems under distribution shift.
This paper analyzes divide-and-conquer estimators for functional linear regression without assuming target function in the RKHS.
problem Functional linear regression without target function in RKHS.
method Integral operator approach to establish upper bounds and prove asymptotic optimality.
result Sharp finite sample upper bounds and asymptotic optimality of divide-and-conquer estimators.
Adaptive source selection for positive transfer in linear models improves target dataset performance.
problem Limited task-specific labeled data in business settings.
method Greedily decides from which sources and how many samples to incorporate into the target dataset using an accept/reject rule based on a data-dependent estimate of the transfer gain.
result Consistent gains over classical and recent strong baselines while avoiding negative transfer.
The goal of transfer learning is to improve the performance of target learning task by leveraging information (or transferring knowledge) from other related tasks. In this paper, we examine the problem of transfer distance metric learning (DML), which usually aims to mitigate the label information deficiency issue in t…
The paper analyzes an actor-critic algorithm with target networks for deep reinforcement learning.
problem Lack of theoretical understanding of target networks in actor-critic methods.
method Proposes a theoretical analysis of an online target-based actor-critic algorithm with linear function approximation.
result Establishes asymptotic convergence results and finite-time analysis for both critic and actor.
Neural networks learn vector fields constrained by linear operators.
problem Learning vector fields from physical systems with linear operator constraints.
method Model the target function as a linear transformation of a potential field, which is a neural network.
result Predictions of the target function satisfy the linear operator constraints.
New methods stabilize Q-learning with linear approximations.
problem Stabilizing Q-learning with linear function approximation. method Target network and truncation.
result Provably stable Q-learning with linear function approximation. This paper consider penalized empirical loss minimization of convex loss functions with unknown non-linear target functions. Using the elastic net penalty we establish a finite sample oracle inequality which bounds the loss of our estimator from above with high probability. If the unknown target is linear this inequali…
The paper investigates how target normalization and momentum affect dying ReLUs in neural networks.
problem Understanding and mitigating the dying ReLU problem in neural networks.
method Empirical analysis and theoretical modeling of a discrete-time linear autonomous system.
result Target variance plays a crucial role in the dying ReLU phenomenon, and momentum exacerbates this issue.
We establish linear regret bounds for convex smooth losses using Fenchel-Young losses.
problem Establishing linear regret bounds for convex smooth losses.
method Constructing a convex smooth surrogate loss using Fenchel-Young losses generated by the convolutional negentropy.
result We derive a smooth loss with a linear surrogate regret bound.
Optimal transport aligns source and target distributions for linear regression in 2D.
problem Domain adaptation for linear regression in 2D with limited target data.
method Combining K-means and optimal transport for estimating geometric transformations.
result Optimal transport recovers geometric transformations like rotations, translations, and homotheties.
Estimates population size using capture-recapture designs with binary indicators.
problem Estimating population size from capture-recapture data with binary indicators.
method Proposes a modern method using undersmoothed lasso model to estimate the target parameter of interest.
result The choice of constraint on the K-dimensional distribution significantly impacts the value of the estimand.
New method detects causal relationships from noisy measurements.
problem Discover causal relationships from noisy, imperfect measurements.
method Transformed Independent Noise (TIN) condition and ordered group decomposition.
result Identifies causal graph structure without over-complete ICA.
Double descent in transfer learning explained for linear regression problems.
problem Understanding generalization errors in transferring parameters between overparameterized linear regression tasks.
method Analytical characterization of generalization error in terms of transfer learning factors.
result Generalization error follows a two-dimensional double descent trend controlled by transfer learning factors.
Improves supervised learning with target-embedding autoencoders.
problem Improving generalization in purely supervised settings with high-dimensional target spaces.
method Target-Embedding Autoencoders (TEA) for jointly optimizing latent representations for prediction and feature predictability.
result Guaranteed generalization for linear TEAs through uniform stability, and empirical validation across multivariate sequence forecasting.
This work extends VQR to non-linear cases and provides scalable solvers.
problem Limitations of VQR in handling non-linear relationships and scalability.
method Extension to non-linear VQR, vector monotone rearrangement, fast solvers.
result Substantial improvement over linear VQR and scalable solvers.
Presents SPEED, an algorithm for optimal policy evaluation in linear bandits with heteroscedastic noise.
problem Optimal data collection for policy evaluation in linear bandits with heteroscedastic reward noise.
method Formulated an optimal design for weighted least squares estimates, derived the optimal sample allocation, introduced SPEED algorithm, and derived regret bounds.
result SPEED leads to policy evaluation with MSE comparable to oracle strategy and significantly lower than random policy execution.
Paper proposes methods to reduce financial contagion by targeted cash injections.
problem Financial contagion through interconnected networks.
method Dynamic model of payments with external control term for corrective cash injections.
result Targeted cash injections can significantly reduce default propagation.
New findings on representation learning beyond linear functions.
problem Achieving diversity in representation learning beyond linear prediction functions.
method Analysis of eluder dimension and empirical risks.
result Diversity holds even with nonlinear prediction functions and multiple layers in neural networks.
The study reveals a linear relationship between source and target domain classification errors based on disagreement.
problem Evaluating model performance under distribution shift with limited labeled data.
method Developed a theoretical foundation for analyzing disagreement in high-dimensional random features regression.
result The disagreement-on-the-line phenomenon occurs when classification error under the source domain is a linear function of the target domain.
TaCo prevents non-linear classifiers from detecting sensitive attributes.
problem Ensuring fairness in NLP models by preventing sensitive attribute detection.
method Targeted Concept Erasure (TaCo) removes sensitive information from final latent representations, even against non-linear classifiers.
result TaCo outperforms state-of-the-art methods in reducing sensitive attribute prediction accuracy while preserving overall task performance.
Improves functional linear regression with shape transfer learning.
problem Data scarcity in functional linear models.
method Shape-based transfer learning from auxiliary to target domains.
result Enhances robustness and generalizability of functional linear models.
ReLU networks trained with MILPs match deep learning accuracy.
problem Training deep neural networks efficiently.
method Iterative training with Mixed Integer Linear Programs (MILPs).
result ReLU networks can be trained with MILPs achieving similar accuracy to deep learning methods.
NKI integrates obfuscated datasets using nonlinear kernels for improved data collaboration.
problem Privacy-preserving data collaboration with reduced reconstruction risk.
method Formulates linear kernel integration, kernelizes it, and introduces graph regularization and centering constraints.
result NKI improves classification accuracy over existing linear integration methods under nonlinear dimensionality reduction.
Databases in domains such as healthcare are routinely released to the public in aggregated form. Unfortunately, naive modeling with aggregated data may significantly diminish the accuracy of inferences at the individual level. This paper addresses the scenario where features are provided at the individual level, but th…
Optimal transport aligns rotated linear regression models across domains.
problem Aligning rotated linear regression models across domains with differing statistical properties.
method Combines K-means clustering, OT, and SVD to estimate rotation angle and adapt regression model.
result Optimal transport map recovers underlying rotation in R2. We consider the problem of tracking a target whose dynamics is modeled by a continuous Itō semi-martingale. The aim is to minimize both deviation from the target and tracking efforts. We establish the existence of asymptotic lower bounds for this problem, depending on the cost structure. These lower bounds can be relat…
New theory explains when pre-trained models can improve downstream tasks.
problem Lack of theoretical understanding of task similarity for transfer learning.
method Feature-centric viewpoint, theoretical results on transferability phase diagram.
result Transfer learning outperforms training from scratch when target task is well represented in feature space.
SignSGD outperforms SGD in linear regression with optimal scaling laws under PLRF model.
problem Improving linear regression performance with signSGD under power-law random features.
method Analysis of signSGD risk under PLRF model, comparison with SGD, identification of unique effects.
result SignSGD can have a steeper compute-optimal slope than SGD in noisy regimes, especially with WSD schedule.
The paper explores optimal algorithms for linear regression under covariate shift, proving the optimality of certain transformations and SGD variants.
problem Optimal algorithms for linear regression under covariate shift with ellipse-shaped constraints.
method Establishes a tight lower generalization bound via Bayesian Cramer-Rao inequality, proves the optimality of certain transformations, and analyzes SGD variants.
result Optimal estimators and SGD variants achieve optimality under specific conditions.
Based on the Hamiltonian dimensional reduction of 3+1 axially symmetric, Ricci-flat Lorentzian spacetimes to a 2+1 Einstein-wave map system with the (negatively curved) hyperbolic 2-plane target, we construct a positive-definite, (spacetime) gauge-invariant energy functional for linear axially symmetric perturbatio…
A simple 2-layer linear network outperforms neural networks in learning sparse targets.
problem Learning sparse targets from a sparse input with gradient descent.
method A 2-layer linear network with fully connected input layer and sparse targets.
result The 2-layer linear network achieves a lower expected square loss than neural networks.
The paper tackles adaptive targeting in networks with interference effects.
problem Adaptive targeting under network interference in a bandit setting.
method Linear model in a sparse regime, analyzing different levels of knowledge of the interference structure.
result Unified view of how knowledge of the interference structure affects online learning efficiency.
Transformers learn low-dimensional target functions efficiently in-context.
problem Efficiently learning nonlinear target functions in-context using transformers.
method Nonlinear MLP layer in transformers optimized by gradient descent, focusing on single-index target functions.
result Transformers can learn target functions with low-dimensional structures efficiently in-context.
The paper improves classification accuracy by leveraging a shared signal across domains in high-dimensional classification.
problem Improving classification accuracy in high-dimensional data with shared signals across domains.
method Transfer learning for linear discriminant analysis, decomposing mean differences into common and domain-specific components.
result Deterministic limits for transfer performance, leading to optimal weights and corrections for bias.
Linear models can overfit without harming OOD generalization under certain conditions.
problem Understanding how overparameterized linear models generalize to out-of-distribution data.
method Analyzing overparameterized linear models under covariate shift, providing guarantees for OOD generalization.
result Benign overfitting occurs in standard ridge regression under OOD conditions, with specific structural conditions on target covariance.
Proposes new models to predict student grades more accurately.
problem Accurately predicting future grades considering prior and concurrent courses.
method Context-aware, non-linear, and neural attentive models.
result Models outperform existing methods in predicting student grades.
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
Paper proposes a statistical test for transfer learning in linear regression.
problem Theoretical framework for parameter transfer in linear regression.
method Developed a statistical test to predict transfer quality.
result The test can predict if a fine-tuned model has lower prediction risk.
The paper improves high-dimensional linear regression prediction and estimation using auxiliary samples.
problem Estimating and predicting high-dimensional linear regression models with auxiliary samples.
method Proposes Trans-Lasso for data-driven transfer learning, establishing optimality for prediction and estimation.
result Knowledge from auxiliary samples can improve learning performance in target problems.