English
Related papers

Related papers: Weight Scope Alignment: A Frustratingly Easy Metho…

200 papers

We study distributed training of deep learning models in time-constrained environments. We propose a new algorithm that periodically pulls workers towards the center variable computed as a weighted average of workers, where the weights are…

Machine Learning · Computer Science 2024-03-08 Tolga Dimlioglu , Anna Choromanska

In model development, model calibration and validation play complementary roles toward learning reliable models. In this article, we expand the Bayesian Validation Metric framework to a general calibration and validation framework by…

Methodology · Statistics 2020-08-04 Tony Tohme , Kevin Vanslette , Kamal Youcef-Toumi

Weight-sharing is ubiquitous in deep learning. Motivated by this, we propose a "weight-sharing regularization" penalty on the weights $w \in \mathbb{R}^d$ of a neural network, defined as $\mathcal{R}(w) = \frac{1}{d - 1}\sum_{i > j}^d |w_i…

Machine Learning · Computer Science 2024-03-12 Mehran Shakerinava , Motahareh Sohrabi , Siamak Ravanbakhsh , Simon Lacoste-Julien

Sequence alignment supports numerous tasks in bioinformatics, natural language processing, pattern recognition, social sciences, and others fields. While the alignment of two sequences may be performed swiftly in many applications, the…

Data Structures and Algorithms · Computer Science 2021-12-06 Eloi Araujo , Luiz Rozante , Diego P. Rubert , Fabio V. Martinez

Low-power chemical sensors deployed on mobile platforms make it possible to monitor pollutant concentrations across large urban areas. However, chemical sensors are prone to drift (e.g., aging, damage, poisoning) and have to be calibrated…

Signal Processing · Electrical Eng. & Systems 2020-06-23 Rakesh Gosangi , Harsha Chenji , Radu Stoleru , Ricardo Gutierrez-Osuna

Robust methods, though ubiquitous in practice, are yet to be fully understood in the context of regularized estimation and high dimensions. Even simple questions become challenging very quickly. For example, classical statistical theory…

Statistics Theory · Mathematics 2023-11-10 Jing Zhou , Gerda Claeskens , Jelena Bradic

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

We revisit the classical, full-fledged Bayesian model averaging (BMA) paradigm to ensemble pre-trained and/or lightly-finetuned foundation models to enhance the classification performance on image and text data. To make BMA tractable under…

Machine Learning · Computer Science 2025-05-29 Mijung Park

This paper examines the quantization methods used in large-scale data analysis models and their hyperparameter choices. The recent surge in data analysis scale has significantly increased computational resource requirements. To address…

Machine Learning · Statistics 2024-01-31 Shuhei Kashiwamura , Ayaka Sakata , Masaaki Imaizumi

Recent developments in Carrillo et al. (2012) and Carrillo et al. (2013) introduced a novel regularization method for compressive imaging in the context of compressed sensing with coherent redundant dictionaries. The approach relies on the…

Information Theory · Computer Science 2013-07-05 Rafael E. Carrillo , Jason D. McEwen , Yves Wiaux

Model merging unifies independently fine-tuned LLMs from the same base, enabling reuse and integration of parallel development efforts without retraining. However, in practice we observe that merging does not always succeed: certain…

Artificial Intelligence · Computer Science 2026-03-11 Yuan Cao , Dezhi Ran , Yuzhe Guo , Mengzhou Wu , Simin Chen , Linyi Li , Wei Yang , Tao Xie

Model merging combines knowledge from separately fine-tuned models, yet the factors driving its success remain poorly understood. While recent work treats mergeability as an intrinsic property of the models, we show with an…

Machine Learning · Computer Science 2026-05-27 Luca Zhou , Bo Zhao , Rose Yu , Emanuele Rodolà

Standard regularization methods typically favor solutions which are in, or close to, the orthogonal complement of the null space of the forward operator/matrix $\mathsf{A}$. This particular biasedness might not be desirable in applications…

Numerical Analysis · Mathematics 2025-09-05 Ole Løseth Elvetun , Bjørn Fredrik Nielsen , Niranjana Sudheer

Federated learning is a collaborative model training method that iterates model updates by multiple clients and aggregation of the updates by a central server. Device and statistical heterogeneity of participating clients cause significant…

Machine Learning · Computer Science 2023-08-29 Ayano Nakai-Kasai , Tadashi Wadayama

Fine-tuning pre-trained models provides significant advantages in downstream performance. The ubiquitous nature of pre-trained models such as BERT and its derivatives in natural language processing has also led to a proliferation of…

Computation and Language · Computer Science 2024-05-06 Thennal D K , Ganesh Nathan , Suchithra M S

Covariate balance is crucial for unconfounded descriptive or causal comparisons. However, lack of balance is common in observational studies. This article considers weighting strategies for balancing covariates. We define a general class of…

Methodology · Statistics 2016-09-30 Fan Li , Kari Lock Morgan , Alan M. Zaslavsky

Covariate balance is crucial for unconfounded descriptive or causal comparisons. However, lack of balance is common in observational studies. This article considers weighting strategies for balancing covariates. We define a general class of…

Methodology · Statistics 2016-11-17 Fan Li , Kari Lock Morgan , Alan M. Zaslavsky

Averaging iterations of Stochastic Gradient Descent (SGD) have achieved empirical success in training deep learning models, such as Stochastic Weight Averaging (SWA), Exponential Moving Average (EMA), and LAtest Weight Averaging (LAWA).…

Machine Learning · Computer Science 2024-11-21 Peng Wang , Li Shen , Zerui Tao , Yan Sun , Guodong Zheng , Dacheng Tao

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network…

Machine Learning · Computer Science 2025-09-19 Haiquan Qiu , You Wu , Dong Li , Jianmin Guo , Quanming Yao

This paper investigates the predictive performance of model averaging in high-dimensional linear regression where the number of regressors is comparable to the sample size. We demonstrate that the double descent trajectory manifests within…

Methodology · Statistics 2026-05-14 Ke Chen , Dandan Jiang , Xinyu Zhang
‹ Prev 1 8 9 10 Next ›