Study on distributional TD learning with linear approximations for better return estimation.
problem Estimating the return distribution of a policy in reinforcement learning.
method Finite-sample analysis of distributional TD learning with linear function approximation, using the linear-categorical Bellman equation and exponential stability arguments for products of random matrices.
result Sample complexity of linear distributional TD learning matches that of classic linear TD learning, indicating similar difficulty in estimating return distribution versus its expectation.
SSL framework identifies non-linear systems without labeled data.
problem System identification in non-linear environments without labeled data.
method Dynamics contrastive learning framework.
result SSL can identify non-linear dynamics in latent space.
Illustrates interleaved learning with Kalman Filter for linear least squares.
problem Improving machine learning algorithms through interleaved learning.
method Simple statistical and optimization framework based on Kalman Filter.
result Demonstrates the effectiveness of interleaved learning.
Framework learns linear programs from optimal decisions.
problem Learning linear programs from optimal decisions is challenging.
method Gradient-based framework for learning linear programs from optimal decisions.
result Successfully learns linear programs and multi-commodity flow instances.
Robust learning mixtures of linear regressions improve robustness.
problem Improving robustness in learning mixtures of linear regressions.
method Connecting mixtures of linear regressions and mixtures of Gaussians with thresholding for a quasi-polynomial time algorithm.
result The algorithm has significantly better robustness than previous results.
The paper provides fast, sample-efficient algorithms for learning common features in multi-task linear regression.
problem Learning transferable features from multiple related tasks.
method Provably fast, sample-efficient algorithms for multi-task linear regression.
result Theoretical guarantees on sample complexity for learning common features.
New algorithms improve distributional TD learning with linear approximations.
problem Estimating return distributions in reinforcement learning.
method Fine-grained analysis of linear-categorical Bellman equation, variance reduction techniques.
result Tight sample complexity bounds for distributional TD learning with linear approximations.
Paper presents a machine learning method to improve significance tests for misspecified linear models.
problem Misspecification of linear assumptions in social science models leads to inaccurate significance levels.
method Apply machine learning to fit ground truth function, calculate linear approximation, and adjust the estimator.
result The method significantly outperforms linear regression for non-linear ground truth functions.
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.
Efficiently extracts linear dynamics from complex observations.
problem Learning policies directly from rich, high-dimensional observations.
method Modeling linear dynamics in a hidden subspace and developing an efficient algorithm.
result Successfully extracts linear dynamics from rich observations.
Analyzes generalization error in generalized linear models, explaining double descent phenomenon.
problem Understanding generalization of machine learning models in high dimensions.
method Develops a framework to characterize asymptotic generalization error for generalized linear models.
result Rigorously explains the double descent phenomenon in generalized linear models.
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.
Linear Q-learning converges to a bounded set without divergence.
problem Proving linear Q-learning does not diverge and converges to a bounded set.
method No modifications to the original linear Q-learning algorithm, no Bellman completeness or near-optimality assumptions, only an ε-softmax behavior policy with adaptive temperature.
result First L 2 L^2 L 2 convergence rate of linear Q-learning iterates to a bounded set. Contrastive learning helps linear models understand document topics.
problem Document classification with limited labeled data.
method Contrastive learning applied to document topic modeling.
result Linear models can recover topic posterior information from contrastive learning representations.
New algorithm learns linear dynamical systems from measurements.
problem Learning system dynamics from linear measurements efficiently and accurately.
method Method of moments estimator to directly estimate Markov parameters.
result First polynomial time algorithm for learning linear dynamical systems.
Paper analyzes agnostic learning of mixed linear regression without generative models.
problem Learning mixed linear regression without assuming stochastic generation.
method Expectation Maximization (EM) and Alternating Minimization (AM) algorithms.
result AM and EM algorithms converge to population loss minimizers under standard conditions.
Linear recurrent networks explain reinforcement learning performance in partially observable settings.
problem Understanding why linear recurrent networks work in reinforcement learning with partial observability.
method Constructed and studied two linear filters for HMMs and action-controlled HMMs.
result Linear filters serve as sufficient statistics and reduce state ambiguity, explaining empirical reinforcement learning success.
Study on dynamics of non-linear autoencoders learning principal components.
problem Technical difficulty in studying non-linear autoencoders due to non-trivial correlations.
method Derive asymptotically exact equations for SGD training of shallow, non-linear autoencoders.
result Autoencoders learn principal components sequentially and tie weights are ineffective.
Safe RL in linear systems achieves T \sqrt{T} T -regret.
problem Efficiently learning in safety-constrained online reinforcement learning.
method Study of linear quadratic regulator with safety constraints.
result First safe algorithm with i l d e O T ( T ) ilde{O}_T(\sqrt{T}) i l d e O T ( T ) -regret. New classifier combines locally linear kernels for fast and accurate non-linear classification.
problem Developing a fast and accurate non-linear classifier.
method Combines locally linear classifiers using a ℓ 1 \ell_1 ℓ 1 Multiple Kernel Learning (MKL) problem with scalable MKL training for streaming kernels. result The resulting classifier achieves high accuracy with fast inference time.
We learn linear models from nonlinear systems using multiple trajectories and regularization.
problem Identifying linear models from data when the underlying dynamics are nonlinear.
method Multiple trajectories data acquisition followed by regularized least squares.
result Learn linearized dynamics with arbitrarily small error given enough samples.
pyLOT library simplifies machine learning on 3D point clouds via linearized optimal transport.
problem Performing machine learning tasks on 3D point clouds.
method Linearized optimal transport (LOT) to embed distributions into Hilbert space, enabling linear machine learning.
result Downstream tasks on embedded representations are simplified to linear operations.
Noise makes learning linear thresholds hard, but algorithms can still learn near-optimal thresholds.
problem Learning linear thresholds in noisy data.
method Exploiting natural assumptions on data-generating process.
result Efficient learning of near-optimal linear thresholds is still possible with small data even in the presence of noise.
Machine learning improves joint default assessment by capturing non-linear dependencies.
problem Capturing non-linear dependencies among covariates for accurate joint default assessment.
method Application of machine learning techniques to credit card dataset, comparing with logistic regression.
result Machine learning outperforms logistic regression in assessing portfolio riskiness.
Proposes σ σ σ -PCA to learn identifiable linear transformations without whitening.
problem Cannot identify axes with equal variances in PCA.
method Unified model for linear and nonlinear PCA, introducing a missing piece to eliminate rotational indeterminacy.
result Eliminates subspace rotational indeterminacy in PCA.
This paper explores the complexity of learning representations in contextual linear bandits.
problem Understanding the complexity of representation learning in contextual linear bandits.
method Systematic approach to representation learning in contextual linear bandits, focusing on instance-dependent perspective.
result Representation learning is fundamentally more complex than linear bandits, with some cases being arbitrarily harder.
Online learning of linear operators between infinite-dimensional spaces is possible but with limitations.
problem Learning linear operators between infinite-dimensional Hilbert spaces in an online setting.
method Online learning approach for linear operators with bounded p p p -Schatten norm, proving impossibility for operator norm. result Separation between online learnability and uniform convergence for bounded linear operators.
SAFLe solves federated learning's trade-off between non-linearity and scalability.
problem Federated Learning's high communication overhead and performance collapse on non-IID data.
method SAFLe introduces a structured head of bucketed features and sparse, grouped embeddings, mathematically equivalent to a high-dimensional linear regression.
result SAFLe achieves a new state-of-the-art in analytic FL, outperforming linear AFL and multi-round DeepAFL.
This paper investigates how data augmentation improves linear separation of manifold data.
problem Understanding how data augmentation enhances linear separation of manifold data.
method Investigates the conditions under which self-supervised representations can linearly separate multi-manifold data.
result Self-supervised learning can linearly separate manifolds with a smaller distance than unsupervised learning.
Paper proposes linear transformers for efficient in-context learning without context length limitations.
problem Quadratic complexity of softmax transformers limits data processing speed.
method Investigates linear transformers under domain generalization, showing they learn mappings from context distributions to response functions.
result Linear transformers achieve in-context learning with a linear complexity in context length, offering a dimension-independent convergence rate.
This paper tackles efficient federated learning for generalized linear bandits.
problem Limited communication efficiency restricts existing federated learning solutions to linear models.
method Proposes a communication-efficient solution framework using online and offline regression.
result Proves sub-linear regret and communication cost for generalized linear bandits.
Meta-learning improves performance in stochastic linear bandits.
problem Selecting a learning algorithm that performs well across multiple bandit tasks.
method Regularized OFUL algorithm with a bias vector, estimating bias within the learning-to-learn setting.
result Meta-learning strategies improve performance when the number of tasks grows and task variance is small.
Weak correlations explain linear dynamics in deep learning models.
problem Understanding the linear structure in gradient-based learning algorithms.
method Characterization of weak correlations between derivatives and parameters.
result Weak correlations are the underlying principle for linearization in deep learning models.
In recent years we see a rapidly growing line of research which shows learnability of various models via common neural network algorithms. Yet, besides a very few outliers, these results show learnability of models that can be learned using linear methods. Namely, such results show that learning neural-networks with gr…
It is important to develop mathematically tractable models than can interpret knowledge extracted from the data and provide reasonable predictions. In this paper, we present a Linear Distillation Learning, a simple remedy to improve the performance of linear neural networks. Our approach is based on using a linear func…
Deep networks prioritize easier examples over harder ones, leading to faster training.
problem Understanding how deep networks prioritize examples of varying difficulty.
method Investigated the effect of linear vs non-linear learning modes on example difficulty.
result Non-linear dynamics tend to sequentialize the learning of examples of increasing difficulty.
New bounds for linear interpolators show how they generalize under covariate shifts.
problem Understanding how linear interpolators generalize under covariate shifts.
method Proved non-asymptotic excess risk bounds for benignly-overfit linear interpolators in transfer learning.
result Identified beneficial and malignant covariate shifts based on overparameterization degree.
A new method combines machine learning with mixed-effects models for better repeated measurement analysis.
problem Inference of linear coefficients in partially linear mixed-effects models with complex interactions and high-dimensional variables.
method Double machine learning approach to estimate nonparametrically nonlinear variables, then use standard linear mixed-effects techniques to estimate the linear coefficient.
result The estimated fixed effects coefficient converges at the parametric rate and is semiparametrically efficient.
Study on neural scaling laws for solving linear systems in-context.
problem Theoretical guarantees for solving linear systems using a linear transformer architecture.
method Neural scaling laws and task diversity for in-domain and out-of-domain generalization.
result Novel notion of task diversity for necessary and sufficient condition of generalization under task shifts.
New bounds for transfer learning in linear models, improving generalization.
problem Understanding when auxiliary data helps in improving generalization in linear models.
method Derivation of exact error bounds and optimal task weights for linear regression and linear neural networks.
result First non-vacuous sufficient conditions for beneficial auxiliary learning in linear neural networks.
Linear Transformer Block combines MLP and linear attention for near-optimal ICL in linear regression.
problem Achieving near-optimal in-context learning (ICL) risk for linear regression with a Gaussian prior.
method Combines linear attention and MLP components in a Linear Transformer Block (LTB). Establishes correspondence with one-step gradient descent estimators ( G D e x t − β \mathsf{GD} ext{-}\mathbfβ GD e x t − β ). result LTB achieves nearly Bayes optimal ICL risk for linear regression with a Gaussian prior.
Study tight offline learning bounds for linear MDPs using variance information.
problem Understanding statistical limits with linear function representations in offline reinforcement learning.
method Variance-aware pessimistic value iteration (VAPVI) that reweights Bellman residuals based on estimated variances.
result Improved offline learning bounds expressed in terms of system quantities.
Transformers can learn noisy linear systems with depth and IID data.
problem Learning noisy linear dynamical systems with transformers.
method Theoretical analysis of multi-layer and single-layer transformers with respect to L 2 L^2 L 2 -testing loss. result Single-layer transformers have a non-diminishing lower bound on approximation error, suggesting depth separation.
New method optimizes offline linear bandits using different confidence sets.
problem Optimizing offline learning for linear contextual bandits.
method Introduces a family of pessimistic learning rules based on ℓ p \ell_p ℓ p confidence sets. result The π ^ ∞ \hatπ_\infty π ^ ∞ rule achieves minimax performance and strictly dominates other predictors. Gradient descent with growing learning rate enables learning non-linear features in neural networks.
problem Learning non-linear features in two-layer neural networks.
method Using gradient descent with a learning rate that grows with the sample size.
result Multiple rank-one components emerge, each corresponding to a specific polynomial feature.
The paper examines efficient algorithms for linear regression over resource-limited networks.
problem Efficient communication in distributed learning over resource-limited networks.
method Developed algorithms for communication-efficient learning of linear regression tasks.
result The algorithms enable a tradeoff between communication and learning with theoretical performance guarantees.
Optimizes PnL using linear signals in quantitative finance.
problem Maximizing profit and loss in financial trading.
method Unsupervised machine learning approach that maximizes Sharpe Ratio through linear relationships and parameter optimization.
result Empirical validation and effectiveness of the model on U.S. Treasury ETF.
FA algorithm provides convergence guarantees for deep linear networks.
problem Training efficiency and convergence of deep neural networks.
method Theoretical analysis of Feedback Alignment (FA) algorithm for deep linear networks.
result Certain initializations lead to implicit anti-regularization, affecting learning effectiveness.