English
Related papers

Related papers: Understanding the Distillation Process from Deep G…

200 papers

Deep generative models (DGMs) for graphs achieve impressively high expressive power thanks to very efficient and scalable neural networks. However, these networks contain non-linearities that prevent analytical computation of many standard…

Machine Learning · Computer Science 2025-08-12 Martin Rektoris , Milan Papež , Václav Šmídl , Tomáš Pevný

Zhang et al. (ICML 2021, PLMR 139, pp. 12447-1245) introduced probabilistic generating circuits (PGCs) as a probabilistic model to unify probabilistic circuits (PCs) and determinantal point processes (DPPs). At a first glance, PGCs store a…

Computational Complexity · Computer Science 2024-04-05 Sanyam Agarwal , Markus Bläser

Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security…

Computer Vision and Pattern Recognition · Computer Science 2026-01-15 Qizhen Lan , Aaron Choi , Jun Ma , Bo Wang , Zhaogming Zhao , Xiaoqian Jiang , Yu-Chun Hsu

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the…

Computation and Language · Computer Science 2021-06-03 Xinyu Wang , Yong Jiang , Zhaohui Yan , Zixia Jia , Nguyen Bach , Tao Wang , Zhongqiang Huang , Fei Huang , Kewei Tu

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Machine Learning · Statistics 2015-10-09 George Papamakarios

The machine learning community has recently put effort into quantized or low-precision arithmetics to scale large models. This paper proposes performing probabilistic inference in the quantized, discrete parameter space created by these…

Machine Learning · Computer Science 2025-08-20 Aleksanteri Sladek , Martin Trapp , Arno Solin

Probabilistic Circuits (PCs) are tractable representations of probability distributions allowing for exact and efficient computation of likelihoods and marginals. Recent advancements have improved the scalability of PCs either by leveraging…

Machine Learning · Computer Science 2025-06-17 Honghua Zhang , Meihua Dang , Benjie Wang , Stefano Ermon , Nanyun Peng , Guy Van den Broeck

Of particular interest is to discover useful representations solely from observations in an unsupervised generative manner. However, the question of whether existing normalizing flows provide effective representations for downstream tasks…

Computer Vision and Pattern Recognition · Computer Science 2022-08-24 Shen Li , Bryan Hooi

Probabilistic circuits (PCs) are a powerful modeling framework for representing tractable probability distributions over combinatorial spaces. In machine learning and probabilistic programming, one is often interested in understanding…

Data Structures and Algorithms · Computer Science 2021-12-10 Yash Pote , Kuldeep S. Meel

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Nikita Starodubcev , Artem Fedorov , Artem Babenko , Dmitry Baranchuk

Probabilistic circuits (PCs) are a class of tractable probabilistic models that allow efficient, often linear-time, inference of queries such as marginals and most probable explanations (MPE). However, marginal MAP, which is central to many…

Artificial Intelligence · Computer Science 2022-03-07 YooJung Choi , Tal Friedman , Guy Van den Broeck

Photorealistic style transfer entails transferring the style of a reference image to another image so the result seems like a plausible photo. Our work is inspired by the observation that existing models are slow due to their large sizes.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-30 Tai-Yin Chiu , Danna Gurari

Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common strategy involves generating multiple Chain-of-Thought (CoT)…

Computation and Language · Computer Science 2025-02-28 Daniele Paliotta , Junxiong Wang , Matteo Pagliardini , Kevin Y. Li , Aviv Bick , J. Zico Kolter , Albert Gu , François Fleuret , Tri Dao

The Tsetlin Machine (TM) is a propositional logic based model that uses conjunctive clauses to learn patterns from data. As with typical neural networks, the performance of a Tsetlin Machine is largely dependent on its parameter count, with…

Artificial Intelligence · Computer Science 2025-04-03 Calvin Kinateder

Large language models (LLMs) excel in complex reasoning tasks, and distilling their reasoning capabilities into smaller models has shown promise. However, we uncover an interesting phenomenon, which we term the Small Model Learnability Gap:…

Artificial Intelligence · Computer Science 2025-11-14 Yuetai Li , Xiang Yue , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Bill Yuchen Lin , Bhaskar Ramasubramanian , Radha Poovendran

Deep Neural Networks have achieved huge success at a wide spectrum of applications from language modeling, computer vision to speech recognition. However, nowadays, good performance alone is not sufficient to satisfy the needs of practical…

Machine Learning · Computer Science 2018-12-31 Xuan Liu , Xiaoguang Wang , Stan Matwin

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Mobarakol Islam , Lalithkumar Seenivasan , S. P. Sharan , V. K. Viekash , Bhavesh Gupta , Ben Glocker , Hongliang Ren

Knowledge distillation allows smaller neural networks to emulate the performance of larger, teacher models with reduced computational demands. Traditional methods for Large Language Models (LLMs) often necessitate extensive fine-tuning,…

Computation and Language · Computer Science 2025-05-02 Tyler McDonald , Ali Emami

Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks. Yet, real-world applications often demand compact models tailored to specific problems. Variants of knowledge distillation have been devised…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Juliette Marrie , Michael Arbel , Julien Mairal , Diane Larlus

Structured prediction models aim at solving a type of problem where the output is a complex structure, rather than a single variable. Performing knowledge distillation for such models is not trivial due to their exponentially large output…

Machine Learning · Computer Science 2022-03-10 Wenye Lin , Yangming Li , Lemao Liu , Shuming Shi , Hai-tao Zheng