English
Related papers

Related papers: How to Parameterize Asymmetric Quantization Ranges…

200 papers

The growing use of large language models has raised environmental and economic concerns about their intensity of resource usage during inference. Serving these models to each user requires substantial energy and water for cooling. Model…

Machine Learning · Computer Science 2025-07-31 Deyu Cao , Samin Aref

With the increased focus on quantum circuit learning for near-term applications on quantum devices, in conjunction with unique challenges presented by cost function landscapes of parametrized quantum circuits, strategies for effective…

Quantum Physics · Physics 2021-09-10 Andrea Skolik , Jarrod R. McClean , Masoud Mohseni , Patrick van der Smagt , Martin Leib

Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem requires incorporating information from multiple datasets - as in…

Machine Learning · Computer Science 2026-04-03 Liyi Zhang , Jake Snell , Thomas L. Griffiths

Regularization, whether explicit in terms of a penalty in the loss or implicit in the choice of algorithm, is a cornerstone of modern machine learning. Indeed, controlling the complexity of the model class is particularly important when…

Machine Learning · Statistics 2024-10-22 Matteo Vilucchio , Nikolaos Tsilivis , Bruno Loureiro , Julia Kempe

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the…

Machine Learning · Computer Science 2026-02-19 Tianyi Chen , Sihan Chen , Xiaoyi Qu , Dan Zhao , Ruomei Yan , Jongwoo Ko , Luming Liang , Pashmina Cameron

We study differentially private model training with stochastic gradient descent under learning rate scheduling and correlated noise. Although correlated noise, in particular via matrix factorizations, has been shown to improve accuracy,…

Machine Learning · Computer Science 2026-05-12 Nikita P. Kalinin , Joel Daniel Andersson

This paper presents an exhaustive study about the robustness of several parameterizations, in speaker verification and identification tasks. We have studied several mismatch conditions: different recording sessions, microphones, and…

Sound · Computer Science 2022-03-02 Marcos Faundez-Zanuy

This paper presents a model-agnostic ensemble approach for supervised learning. The proposed approach is based on a parametric version of Random Subspace, in which each base model is learned from a feature subset sampled according to a…

Machine Learning · Computer Science 2023-01-23 Vân Anh Huynh-Thu , Pierre Geurts

In the era of noisy intermediate-scale quantum (NISQ), variational quantum circuits (VQCs) have been widely applied in various domains, demonstrating the potential advantages of quantum circuits over classical models. Similar to classic…

Quantum Physics · Physics 2025-08-26 Jun Zhuang , Jack Cunningham , Chaowen Guan

Graph Hypernetworks (GHN) can predict the parameters of varying unseen CNN architectures with surprisingly good accuracy at a fraction of the cost of iterative optimization. Following these successes, preliminary research has explored the…

Machine Learning · Computer Science 2023-09-26 Stone Yun , Alexander Wong

Transformer language models such as GPT-2 are difficult to quantize because of outliers in activations leading to a large quantization error. To adapt to the error, one must use quantization-aware training, which entails a fine-tuning…

Machine Learning · Computer Science 2022-12-01 Minseop Park , Jaeseong You , Markus Nagel , Simyung Chang

In the presented study, we discover that the so-called "transition freedom" metric appears superior for unsupervised tokenization purposes in comparison to statistical metrics such as mutual information and conditional probability,…

Computation and Language · Computer Science 2022-12-16 Anton Kolonin , Vignav Ramesh

Quantization techniques commonly reduce the inference costs of neural networks by restricting the precision of weights and activations. Recent studies show that also reducing the precision of the accumulator can further improve hardware…

Machine Learning · Computer Science 2024-01-22 Ian Colbert , Alessandro Pappalardo , Jakoba Petri-Koenig , Yaman Umuroglu

Quantization-aware training (QAT) is widely adopted to quantize language models by training full-precision weights using gradients from the quantized model. The main bottleneck is its slow convergence and early performance plateau,…

As machine learning applications grow increasingly ubiquitous and complex, they face an increasing set of requirements beyond accuracy. The prevalent approach to handle this challenge is to aggregate a weighted combination of requirement…

Machine Learning · Computer Science 2026-01-07 Aneesh Barthakur , Luiz F. O. Chamon

Quantization techniques applied to the inference of deep neural networks have enabled fast and efficient execution on resource-constraint devices. The success of quantization during inference has motivated the academic community to explore…

Machine Learning · Computer Science 2021-05-11 Marios Fournarakis , Markus Nagel

Model miscalibration has been frequently identified in modern deep neural networks. Recent work aims to improve model calibration directly through a differentiable calibration proxy. However, the calibration produced is often biased due to…

Machine Learning · Computer Science 2024-06-26 Cheng Wang , Jacek Golebiowski

One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i.e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical…

Machine Learning · Statistics 2020-07-17 Rares-Darius Buhai , Yoni Halpern , Yoon Kim , Andrej Risteski , David Sontag

Neural-based image and video codecs are significantly more power-efficient when weights and activations are quantized to low-precision integers. While there are general-purpose techniques for reducing quantization effects, large losses can…

Image and Video Processing · Electrical Eng. & Systems 2023-01-26 Amir Said , Reza Pourreza , Hoang Le

In this paper we study the effects of quantization in DNN training. We hypothesize that weight quantization is a form of regularization and the amount of regularization is correlated with the quantization level (precision). We confirm our…