paper-with-me

홈 › Papers

A Short Information-Theoretic Analysis of Linear Auto-Regressive Learning

2024-09-10 · Ingvar Ziemann

In this note, we give a short information-theoretic proof of the consistency of the Gaussian maximum likelihood estimator in linear auto-regressive models. Our proof yields nearly optimal non-asymptotic rates for parameter recovery and works without any invocation of stability in the case of finite hypothesis classes.

📄 PDF Abstract BibTeX arXiv:2409.06437

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Edge of stability echo state networks

2023-08-05 · Andrea Ceni, Claudio Gallicchio

Echo State Networks (ESNs) are time-series processing models working under the Echo State Property (ESP) principle. The ESP is a notion of stability that imposes an asymptotic fading of the memory of the input. On the ot…

Estimating Linguistic Complexity for Science Texts

2018-06-01 · WS 2018 6 · Farah Nadeem, Mari Ostendorf

Evaluation of text difficulty is important both for downstream tasks like text simplification, and for supporting educators in classrooms. Existing work on automated text complexity analysis uses linear models with engin…

Feature EngineeringReading ComprehensionText Simplification

From Linearity to Non-Linearity: How Masked Autoencoders Capture Spatial Correlations

2025-08-21 · Anthony Bisulco, Rahul Ramesh, Randall Balestriero, Pratik Chaudhari arxiv

Masked Autoencoders (MAEs) have emerged as a powerful pretraining technique for vision foundation models. Despite their effectiveness, they require extensive hyperparameter tuning (masking ratio, patch size, encoder/deco…

It's Enough: Relaxing Diagonal Constraints in Linear Autoencoders for Recommendation

2023-05-22 · Jaewan Moon, Hye-Young Kim, Jongwuk Lee

Linear autoencoder models learn an item-to-item weight matrix via convex optimization with L2 regularization and zero-diagonal constraints. Despite their simplicity, they have shown remarkable performance compared to sop…

DenoisingL2 Regularization

Information Theoretic Analysis of DNN-HMM Acoustic Modeling

2017-08-29 · Pranay Dighe, Afsaneh Asaei, Hervé Bourlard

We propose an information theoretic framework for quantitative assessment of acoustic modeling for hidden Markov model (HMM) based automatic speech recognition (ASR). Acoustic modeling yields the probabilities of HMM sub…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition