English
Related papers

Related papers: Distilling Policy Distillation

200 papers

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature representations that…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Zhizhong Li , Avinash Ravichandran , Charless Fowlkes , Marzia Polito , Rahul Bhotika , Stefano Soatto

Knowledge transfer between artificial neural networks has become an important topic in deep learning. Among the open questions are what kind of knowledge needs to be preserved for the transfer, and how it can be effectively achieved.…

Computer Vision and Pattern Recognition · Computer Science 2022-10-03 Vladimir Li , Atsuto Maki

Distillation is the task of replacing a complicated machine learning model with a simpler model that approximates the original [BCNM06,HVD15]. Despite many practical applications, basic questions about the extent to which models can be…

Machine Learning · Computer Science 2024-05-07 Enric Boix-Adsera

Knowledge distillation is a widely applicable technique for training a student neural network under the guidance of a trained teacher network. For example, in neural network compression, a high-capacity teacher is distilled to train a…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Frederick Tung , Greg Mori

Much of the focus in the area of knowledge distillation has been on distilling knowledge from a larger teacher network to a smaller student network. However, there has been little research on how the concept of distillation can be leveraged…

Neural and Evolutionary Computing · Computer Science 2019-01-29 Zhong Qiu Lin , Alexander Wong

Language model (LM) post-training (or alignment) involves maximizing a reward function that is derived from preference annotations. Direct Preference Optimization (DPO) is a popular offline alignment method that trains a policy directly on…

Machine Learning · Computer Science 2025-03-04 Adam Fisch , Jacob Eisenstein , Vicky Zayats , Alekh Agarwal , Ahmad Beirami , Chirag Nagpal , Pete Shaw , Jonathan Berant

The burgeoning complexity of contemporary deep learning models, while achieving unparalleled accuracy, has inadvertently introduced deployment challenges in resource-constrained environments. Knowledge distillation, a technique aiming to…

Machine Learning · Computer Science 2023-10-05 Sia Gholami , Marwan Omar

Deep Reinforcement Learning is one of the state-of-the-art methods for producing near-optimal system controllers. However, deep RL algorithms train a deep neural network, that lacks transparency, which poses challenges when the controller…

Machine Learning · Computer Science 2025-11-18 Senne Deproost , Dennis Steckelmacher , Ann Nowé

Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algorithm, building on the CN2 rule mining algorithm, that…

Artificial Intelligence · Computer Science 2021-06-14 Youri Coppens , Denis Steckelmacher , Catholijn M. Jonker , Ann Nowé

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Machine Learning · Computer Science 2026-01-12 Pattarawat Chormai , Ali Hashemi , Klaus-Robert Müller , Grégoire Montavon

Knowledge distillation (KD) is a powerful paradigm for compressing large language models (LLMs), whose effectiveness depends on intertwined choices of divergence direction, optimization strategy, and data regime. We break down the design of…

Computation and Language · Computer Science 2026-04-23 Wenhong Zhu , Ruobing Xie , Rui Wang , Pengfei Liu

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Computation and Language · Computer Science 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep the model fixed and instead attempt to distill the knowledge…

Machine Learning · Computer Science 2020-02-26 Tongzhou Wang , Jun-Yan Zhu , Antonio Torralba , Alexei A. Efros

Deep neural network architectures have attained remarkable improvements in scene understanding tasks. Utilizing an efficient model is one of the most important constraints for limited-resource devices. Recently, several compression methods…

Computer Vision and Pattern Recognition · Computer Science 2020-10-12 Mahdi Ghorbani , Fahimeh Fooladgar , Shohreh Kasaei

Knowledge distillation has emerged as an effective strategy for compressing large language models' (LLMs) knowledge into smaller, more efficient student models. However, standard one-shot distillation methods often produce suboptimal…

Computation and Language · Computer Science 2025-04-04 Kushal Jain , Piyushi Goyal , Kumar Shridhar

Despite success in many challenging problems, reinforcement learning (RL) is still confronted with sample inefficiency, which can be mitigated by introducing prior knowledge to agents. However, many transfer techniques in reinforcement…

Machine Learning · Computer Science 2022-09-21 Matheus Centa , Philippe Preux

Dataset distillation, a pragmatic approach in machine learning, aims to create a smaller synthetic dataset from a larger existing dataset. However, existing distillation methods primarily adopt a model-based paradigm, where the synthetic…

Machine Learning · Computer Science 2024-02-21 Binglin Zhou , Linhao Zhong , Wentao Chen

We explore best practices for training small, memory efficient machine translation models with sequence-level knowledge distillation in the domain adaptation setting. While both domain adaptation and knowledge distillation are widely-used,…

Computation and Language · Computer Science 2020-06-24 Mitchell A. Gordon , Kevin Duh

The aim of dataset distillation is to encode the rich features of an original dataset into a tiny dataset. It is a promising approach to accelerate neural network training and related studies. Different approaches have been proposed to…

Machine Learning · Computer Science 2023-05-30 Zongxiong Chen , Jiahui Geng , Derui Zhu , Herbert Woisetschlaeger , Qing Li , Sonja Schimmler , Ruben Mayer , Chunming Rong

Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning techniques, is vulnerable to adversarial…

Cryptography and Security · Computer Science 2016-03-15 Nicolas Papernot , Patrick McDaniel , Xi Wu , Somesh Jha , Ananthram Swami