On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

48 results for “low rank representation”

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPscs.LG

FLAMBE tackles RL in low rank MDPs by learning features.

problem Dealing with the curse of dimensionality in RL.

method Develops FLAMBE, a method that engages in exploration and representation learning for RL in low rank transition models.

result FLAMBE efficiently learns features for RL in low rank transition models.

reinforcement learning low rank MDPs representation learning latent variable models matrix decomposition

2020-06-18abs ↗pdf ↗

Model-free Representation Learning and Exploration in Low-rank MDPscs.LG

New model-free algorithms learn representations for low-rank MDPs efficiently.

problem Learning representations in reinforcement learning for low-rank MDPs.

method Developed minimax representation learning objective and interleaved with reward-free exploration.

result Proven sample efficiency and scalability to complex environments.

representation learning reinforcement learning minimax low-rank MDPs exploration

2021-02-14abs ↗pdf ↗

Representation Learning for Online and Offline RL in Low-rank MDPscs.LG

This work tackles representation learning for RL in low-rank MDPs, improving sample efficiency.

problem How to learn a compact representation for RL in low-rank MDPs efficiently.

method Proposes REP-UCB for online RL and develops an algorithm for offline RL under partial coverage.

result Significantly improved sample complexity for online RL and competitive performance for offline RL.

representation learning online RL offline RL low-rank MDPs upper confidence bound

2021-10-09abs ↗pdf ↗

Adversarial robustness via robust low rank representationscs.LG

This work improves robustness guarantees for neural networks using low rank representations.

problem Certified robustness to adversarial perturbations in neural networks.

method Low rank representations to provide improved robustness guarantees.

result Improved robustness guarantees for

\ell_\infty

perturbations using natural low rank representations.

robustness neural networks low rank adversarial certified

2020-07-13abs ↗pdf ↗

Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPscs.LG

Paper improves sample complexity for reward-free RL in low-rank MDPs.

problem Reward-free RL in low-rank MDPs with unknown representation and weights.

method Proposes a novel model-based algorithm RAFFLE with improved sample complexity.

result RAFFLE achieves

ε

-optimal policy and accurate system identification with significantly fewer samples.

reinforcement learning reward-free low-rank MDPs sample complexity algorithm

2023-03-20abs ↗pdf ↗

Sequences of Logits Reveal the Low Rank Structure of Language Modelscs.LG

Language models exhibit low-rank structure, which can be used for generation.

problem Understanding the low-dimensional structure of large language models.

method Empirical demonstration and theoretical analysis of the approximate rank of language models' logits.

result Language models can generate responses using linear combinations of unrelated prompts.

language models low-rank structure logits sequential models representation power

2025-10-28abs ↗pdf ↗

Multi-task Representation Learning with Stochastic Linear Banditsstat.ML

Study multi-task learning with low-rank representation in stochastic linear bandits.

problem Transfer learning across multiple linear bandit tasks with shared low-dimensional representation.

method Proposes a greedy policy with trace norm regularization to implicitly learn a low-rank representation without knowing the rank.

result Upper bound on multi-task regret of

\sqrt{NdT(T+d)r}

, showing benefit over independent task solving.

multi-task learning stochastic linear bandits low-rank representation trace norm regularization regret analysis

2022-02-21abs ↗pdf ↗

Low-Rank Plus Sparse Matrix Transfer Learning under Growing Representations and Ambient Dimensionscs.LG

The paper tackles transfer learning for growing matrix representations, improving estimation accuracy.

problem Structured matrix estimation under growing ambient dimensions and latent representations.

method Proposes a general transfer framework decomposing target parameters into embedded source components, low-rank innovations, and sparse edits. Develops an anchored alternating projection estimator.

result Establishes deterministic error bounds that separate target noise, representation growth, and source estimation error, yielding improved rates.

transfer learning matrix estimation low-rank sparse growing dimensions

2026-01-29abs ↗pdf ↗

Robustness via Deep Low-Rank Representationscs.LG

We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations, we propose an easy-to-use, end-to-end trainable, low-rank regularizer (LR) that…

2018-04-19abs ↗pdf ↗

Tensor Methods for Nonlinear Matrix Completionstat.ML

In the low-rank matrix completion (LRMC) problem, the low-rank assumption means that the columns (or rows) of the matrix to be completed are points on a low-dimensional linear algebraic variety. This paper extends this thinking to cases where the columns are points on a low-dimensional nonlinear algebraic variety, a pr…

2018-04-26abs ↗pdf ↗

Matrix Approximation under Local Low-Rank Assumptioncs.LG

Matrix approximation is a common tool in machine learning for building accurate prediction models for recommendation systems, text mining, and computer vision. A prevalent assumption in constructing matrix approximations is that the partially observed matrix is of low-rank. We propose a new matrix approximation model w…

2013-01-15abs ↗pdf ↗

Provably Efficient CVaR RL in Low-rank MDPscs.LG

New RL algorithm maximizes CVaR in low-rank MDPs with provable efficiency.

problem Maximizing CVaR in large state spaces with function approximation.

method Upper Confidence Bound (UCB) bonus-driven algorithm for low-rank MDPs.

result Achieves sample complexity of O(H^7 A^2 d^4 / τ^2 ε^2) for ε-optimal CVaR.

Reinforcement Learning Conditional Value at Risk Low-rank MDPs Upper Confidence Bound Function Approximation

2023-11-20abs ↗pdf ↗

Efficient Low-rank Multimodal Fusion with Modality-Specific Factorscs.AI

Multimodal research is an emerging field of artificial intelligence, and one of the main research problems in this field is multimodal fusion. The fusion of multimodal data is the process of integrating multiple unimodal representations into one compact multimodal representation. Previous research in this field has exp…

2018-05-31abs ↗pdf ↗

TT-NF: Tensor Train Neural Fieldscs.LG

Introduces TT-NF for more compact neural field representations.

problem Finding more compact and easy-to-fit neural field representations.

method Tensor Train parameterization trained with backpropagation.

result Low-rank compression improves downstream task quality metrics.

Tensor Train Neural Fields Low-rank Tensor Denoising Neural Radiance Fields

2022-09-30abs ↗pdf ↗

Robust Data Clustering with Outliers via Transformed Tensor Low-Rank Representationstat.ML

Paper develops a method to robustly cluster tensors with outliers.

problem Clustering tensors contaminated by outliers or sample-specific corruptions.

method Transformed Tensor Low-Rank Representation (OR-TLRR) method.

result Provably recovers row space of clean data and detects outliers.

Tensor Clustering Outliers Robustness Low-Rank Representation t-SVD

2023-07-18abs ↗pdf ↗

Multi-Level Network Embedding with Boosted Low-Rank Matrix Approximationcs.SI

As opposed to manual feature engineering which is tedious and difficult to scale, network representation learning has attracted a surge of research interests as it automates the process of feature learning on graphs. The learned low-dimensional node vector representation is generalizable and eases the knowledge discove…

2018-08-26abs ↗pdf ↗

Experimental Analysis of Legendre Decomposition in Machine Learningcs.LG

The report analyzes Legendre decomposition for tensor data.

problem Finding effective lower dimensional representations of tensors.

method Theoretical analysis of dual parameters and dually flat manifold properties, followed by experimental verification and clustering.

result Parameters on submanifold cannot be directly used as low-rank representations.

Legendre decomposition tensor decomposition machine learning non-negative tensors neural networks

2020-08-12abs ↗pdf ↗

Graph Contrastive Learning with Low-Rank Regularization and Low-Rank Attention for Noisy Node Classificationcs.LG

GCL-LRR improves node classification in noisy graphs.

problem Noise in real-world graph data impairs GNNs' effectiveness.

method Two-stage transductive learning with low-rank regularization and attention.

result Improved node classification performance in noisy graphs.

Graph Neural Networks Node Classification Low-Rank Regularization Low-Rank Attention Transductive Learning

2024-02-14abs ↗pdf ↗

Stochastic Linear Bandits with Hidden Low Rank Structurecs.LG

High-dimensional representations often have a lower dimensional underlying structure. This is particularly the case in many decision making settings. For example, when the representation of actions is generated from a deep neural network, it is reasonable to expect a low-rank structure whereas conventional structures l…

2019-01-28abs ↗pdf ↗

LogDet Rank Minimization with Application to Subspace Clusteringcs.CV

Low-rank matrix is desired in many machine learning and computer vision problems. Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator. However, all singular values are simply added together by the nuclear norm, and thus the rank may not be well approximated in practical problems. …

2015-07-03abs ↗pdf ↗

Low Rank and Sparse Fourier Structure in Recurrent Networks Trained on Modular Additioncs.LG

RNNs solve modular addition tasks using low rank and sparse Fourier structures.

problem Solving modular addition tasks with recurrent neural networks.

method Identified low rank structures and sparse Fourier representations in RNN weights.

result RNNs robust to removing individual frequencies but degrade with more ablation.

Recurrent Neural Networks Fourier Multiplication Modular Addition Low Rank Structure Sparse Representation

2025-03-28abs ↗pdf ↗

Nonlinear time-series embedding by monotone variational inequalitycs.LG

New method learns low-dimensional representations of nonlinear time series without supervision.

problem Learning low-dimensional representations of nonlinear time series without supervision.

method Based on monotone variational inequality, the method learns representations by assuming sequences arise from a common domain.

result The method can learn the geometry for the entire domain and faithful representations for the dynamics of each individual sequence.

time series nonlinear dynamics representation learning variational inequality monotonicity

2024-06-11abs ↗pdf ↗

An Overview of Low-Rank Structures in the Training and Adaptation of Large Modelscs.LG

Research reveals deep networks often learn low-rank structures, leading to more efficient training and fine-tuning.

problem Efficient training and deployment of large-scale deep learning models.

method Complementary theoretical perspectives on low-rank structures during training and convergence, and practical applications of LoRA and masked training.

result Understanding and exploiting low-rank structures can improve efficiency and effectiveness of training and fine-tuning.

low-rank structures deep learning gradient descent optimization fine-tuning

2025-03-25abs ↗pdf ↗

Multi-View Spectral Clustering Tailored Tensor Low-Rank Representationcs.LG

Paper improves MVSC using tensor low-rank modeling.

problem Improving multi-view spectral clustering.

method Structured tensor low-rank norm for MVSC optimization.

result Proposed method outperforms state-of-the-art methods.

multi-view spectral clustering tensor low-rank structured tensor MVSC optimization augmented Lagrange multiplier

2020-04-30abs ↗pdf ↗

Low-Rank Inducing Norms with Optimality Interpretationsmath.OC

Optimization problems with rank constraints appear in many diverse fields such as control, machine learning and image analysis. Since the rank constraint is non-convex, these problems are often approximately solved via convex relaxations. Nuclear norm regularization is the prevailing convexifying technique for dealing …

2016-12-09abs ↗pdf ↗

Meta-learning of shared linear representations beyond well-specified linear regressioncs.LG

New method learns shared structures in non-linear tasks.

problem Learning shared linear representations in non-linear tasks.

method Convex optimization with structural assumptions.

result Rank and clustered estimators recover shared structures under certain conditions.

meta-learning convex optimization low-rank representations clustered structures Hessian concentration

2025-01-31abs ↗pdf ↗

We propose a novel method of introducing structure into existing machine learning techniques by developing structure-based similarity and distance measures. To learn structural information, low-dimensional structure of the data is captured by solving a non-linear, low-rank representation problem. We show that this low-…

2011-10-26abs ↗pdf ↗

Low-Rank Tensors for Multi-Dimensional Markov Modelseess.SY

A low-rank tensor model simplifies multi-dimensional Markov chains.

problem Simplifying the dynamics of multi-dimensional Markov chains.

method Low-rank tensor decomposition for multi-dimensional state spaces.

result Our tensor model requires fewer parameters and samples than conventional methods.

Markov chains multi-dimensionality low-rank tensors tensor decomposition ADMM optimization

2024-11-04abs ↗pdf ↗

Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedbackcs.LG

Algorithm POLO learns low-rank MDPs with adversarial changes in full-info feedback.

problem Learning low-rank MDPs with adversarial changes and unknown transition probabilities.

method Policy optimization-based algorithm POLO with regret guarantee.

result POLO achieves sublinear regret guarantee with no dependence on state space size.

Adversarial MDPs Low-rank MDPs Policy Optimization Regret Minimization Oracle-Efficiency

2023-11-14abs ↗pdf ↗

Learning Good State and Action Representations via Tensor Decompositionstat.ML

Paper learns meaningful state and action representations from MDP trajectories.

problem Learning good state and action representations from MDP trajectories.

method Tensor decomposition, kernelization, importance sampling, low-Tucker-rank approximation.

result The learned state/action abstractions provide accurate approximations to latent block structures.

Tensor decomposition Markov decision process State representation Action representation Low-Tucker-rank approximation

2021-05-03abs ↗pdf ↗

Implicit Rank-Minimizing Autoencodercs.LG

IRMAE learns compact latent spaces by minimizing rank.

problem Learning compact latent representations in autoencoders.

method Implicitly minimizes the rank of the covariance matrix through gradient descent in multi-layer linear networks.

result Demonstrates validity on image generation and representation learning tasks.

autoencoder latent space rank minimization gradient descent compact representation

2020-10-01abs ↗pdf ↗

ADARL: Adaptive Low-Rank Structures for Robust Policy Learning under Uncertaintycs.LG

AdaRL improves robust RL by adaptively adjusting policy complexity.

problem Handling epistemic uncertainty in environment dynamics.

method Bi-level optimization framework with adaptive rank adjustment.

result AdaRL outperforms existing methods on MuJoCo benchmarks.

Robust RL Adaptive Rank Wasserstein Ball MuJoCo Policy Optimization

2025-10-13abs ↗pdf ↗

Representation Learning for General-sum Low-rank Markov Gamescs.LG

Algorithm finds ε-equilibrium policies for multi-agent Markov games with hidden low-rank structure.

problem Designing efficient algorithms for multi-agent Markov games with unknown representation and hidden low-rank structure.

method Model-based and model-free approaches using representation learning to construct an effective representation from data.

result Achieves poly

(H,d,A,1/\varepsilon)

sample complexity for both model-based and model-free approaches.

Markov Games Representation Learning Equilibrium Policies Deep Learning Function Approximation

2022-10-30abs ↗pdf ↗

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoffcs.LG

Large neural networks learn low-dimensional representations that balance complexity and regularity.

problem Understanding the tradeoff between low-dimensional representations and complexity in deep neural networks.

method Computed finite depth corrections to reveal a measure of regularity that bounds the pseudo-determinant of the Jacobian.

result Proved the conjectured bottleneck structure in learned features as network depth increases, showing almost all hidden representations are approximately low-dimensional and weight matrices have singular values close to 1.

Deep Learning Neural Networks Bottleneck Structure Regularization Rank

2023-05-30abs ↗pdf ↗

Low-Rank Correction for Quantized LLMsstat.ML

New method corrects quantization errors in LLMs using low-rank matrices.

problem Correcting quantization errors in large language models.

method Introducing low-rank weight matrices to correct quantized activations in LLMs.

result Reduces accuracy gap with original model by more than 50% using low-rank matrices.

model compression quantization errors large language models LLMs low-rank correction

2024-12-10abs ↗pdf ↗

Implicit Bias in Matrix Factorization and its Explicit Realization in a New Architecturecs.LG

New model reduces matrix factorization bias, yielding truly low-rank solutions.

problem Gradient descent's implicit bias in matrix factorization.

method Introducing a new factorization model with constrained factors and diagonal components.

result The new model consistently exhibits a strong implicit bias, yielding truly low-rank solutions.

matrix factorization gradient descent implicit bias low-rank solutions norm balls

2025-01-27abs ↗pdf ↗

Low-Rank MDPs with Continuous Action Spacescs.LG

New method extends low-rank MDPs to continuous action spaces.

problem Limited applicability of current low-rank MDP methods to continuous action spaces.

method Extending FLAMBE algorithm to continuous action spaces with Hölder smoothness conditions.

result Similar PAC bound achieved for continuous actions with polynomial dependence on smoothness order.

reinforcement learning Markov Decision Processes continuous actions Hölder smoothness PAC bounds

2023-11-06abs ↗pdf ↗

Tensor Convolutional Sparse Coding with Low-Rank activations, an application to EEG analysiscs.LG

New CSC model extracts EEG signals with low noise sensitivity.

problem Analyzing noisy EEG signals during anesthesia.

method Kruskal CSC model using Kruskal decomposition for low-rank tensor activations.

result TC-FISTA efficiently extracts robust, sparse, and interpretable EEG encodings.

EEG analysis Tensor Convolutional Sparse Coding Low-rank activations General Anesthesia Kruskal decomposition

2020-07-06abs ↗pdf ↗

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in

L^2

-Regularized Nonlinear Networkscs.LG

The paper connects neural collapse and low-rank bias in networks with L2 regularization.

problem Understanding the emergence of low-rank bias and neural collapse in L2-regularized networks.

method Unified theoretical framework linking TCV and rank of weight matrices, proving global optimality of DNC1, and establishing a benign landscape property.

result Zero TCV across intermediate layers minimizes representation cost under natural architectural constraints, and DNC1 is globally optimal.

Deep Neural Collapse Low-Rank Bias L2 Regularization Total Cluster Variation Weight Decay

2024-02-06abs ↗pdf ↗

Parallel Gaussian Process Regression for Big Data: Low-Rank Representation Meets Markov Approximationstat.ML

The expressive power of a Gaussian process (GP) model comes at a cost of poor scalability in the data size. To improve its scalability, this paper presents a low-rank-cum-Markov approximation (LMA) of the GP model that is novel in leveraging the dual computational advantages stemming from complementing a low-rank appro…

2014-11-17abs ↗pdf ↗

Low-rank Optimization with Convex Constraintsmath.OC

The problem of low-rank approximation with convex constraints, which appears in data analysis, system identification, model order reduction, low-order controller design and low-complexity modelling is considered. Given a matrix, the objective is to find a low-rank approximation that meets rank and convex constraints, w…

2016-06-06abs ↗pdf ↗

Seq2Tens: An Efficient Representation of Sequences by Low-Rank Tensor Projectionscs.LG

Seq2Tens uses tensors to efficiently represent sequences, improving performance on time series and video tasks.

problem Challenges in analyzing sequential data due to complex dependencies and non-commutativity.

method Uses tensor algebra to capture dependencies and low-rank tensor projections to manage computational complexity.

result State-of-the-art performance on multivariate time series classification and video generation benchmarks.

tensor algebra sequence representation low-rank projections neural networks time series

2020-06-12abs ↗pdf ↗

Multi-view Low-rank Preserving Embedding: A Novel Method for Multi-view Representationcs.LG

Proposes MvLPE for better multi-view representation learning.

problem Learning representations from multi-view data with varying correlations.

method Integrates multi-view data into a centroid view while maintaining low-rank reconstruction relations.

result MvLPE outperforms existing methods on benchmark datasets.

multi-view learning representation low-rank preserving centroid view multi-view information fusion

2020-06-14abs ↗pdf ↗

Unsupervised Hypergraph Feature Selection via a Novel Point-Weighting Framework and Low-Rank Representationcs.LG

Feature selection methods are widely used in order to solve the 'curse of dimensionality' problem. Many proposed feature selection frameworks, treat all data points equally; neglecting their different representation power and importance. In this paper, we propose an unsupervised hypergraph feature selection method via …

2018-08-25abs ↗pdf ↗

Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guaranteesstat.ML

The paper establishes theoretical foundations for low-rank knowledge distillation in LLMs.

problem Understanding the theoretical underpinnings of low-rank knowledge distillation in LLMs.

method Theoretical framework for low-rank knowledge distillation, including convergence rates and generalization bounds.

result Theoretical analysis reveals optimal rank

r^* = O(\sqrt{n})

for minimizing generalization error.

Knowledge Distillation Large Language Models Low-Rank Projection Convergence Rates Generalization Bounds

2026-03-22abs ↗pdf ↗

Learning Representations from Imperfect Time Series Data via Tensor Rank Regularizationcs.LG

There has been an increased interest in multimodal language processing including multimodal dialog, question answering, sentiment analysis, and speech recognition. However, naturally occurring multimodal data is often imperfect as a result of imperfect modalities, missing entries or noise corruption. To address these c…

2019-07-01abs ↗pdf ↗

Asymptotic Normality of Generalized Low-Rank Matrix Sensing via Riemannian Geometrystat.ML

New method proves asymptotic normality for matrix sensing problems.

problem Proving asymptotic normality for matrix sensing under general convex losses.

method Riemannian geometry to handle degeneracy of the Hessian due to rotational symmetry.

result Proves

\sqrt{n}(φ^0-φ^*)\xrightarrow{D}N(0,(H^*)^{-1})

n o\infty

matrix sensing asymptotic normality Riemannian geometry low-rank matrices convex loss

2024-07-14abs ↗pdf ↗

Joint Tensor-Train Parameterization for Efficient and Expressive Low-Rank Adaptationcs.LG

TensorGuide improves LoRA efficiency and expressivity through joint tensor-train optimization.

problem Limited expressivity and generalization of standard LoRA.

method TensorGuide uses a unified tensor-train structure with controlled Gaussian noise to generate correlated low-rank matrices.

result TensorGuide achieves superior accuracy and scalability with fewer parameters compared to standard LoRA and TT-LoRA.

TensorGuide LoRA Tensor-train Parameter-efficient Fine-tuning

2025-06-19abs ↗pdf ↗