中文
相关论文

相关论文: The Symmetric Perceptron: a Teacher-Student Scenar…

200 篇论文

We characterize the equilibrium properties of a model of $y$ coupled binary perceptrons in the teacher-student scenario, subject to a suitable cost function, with an explicit ferromagnetic coupling proportional to the Hamming distance…

无序系统与神经网络 · 物理学 2024-07-02 Giovanni Catania , Aurélien Decelle , Beatriz Seoane

One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with the single-layer teacher-student perceptron on i.i.d. Gaussian inputs. Both…

We introduce a novel semi-supervised learning approach, named Teacher-Student Bayesian Optimization ($\texttt{TSBO}$), integrating the teacher-student paradigm into BO to minimize expensive labeled data queries for the first time.…

机器学习 · 计算机科学 2024-10-25 Yuxuan Yin , Yu Wang , Peng Li

Learning behavior of simple perceptrons is analyzed for a teacher-student scenario in which output labels are provided by a teacher network for a set of possibly correlated input patterns, and such that teacher and student networks are of…

无序系统与神经网络 · 物理学 2016-12-15 Takashi Shinzato , Yoshiyuki Kabashima

In this paper, we consider a recently-proposed model of teaching and learning under uncertainty, in which a teacher receives independent observations of a single bit corrupted by binary symmetric noise, and sequentially transmits to a…

信息论 · 计算机科学 2022-12-09 Yan Hao Ling , Jonathan Scarlett

We consider optimal sensor placement for hyper-parameterized linear Bayesian inverse problems, where the hyper-parameter characterizes nonlinear flexibilities in the forward model, and is considered for a range of possible values. This…

数值分析 · 数学 2020-11-24 Nicole Aretz-Nellesen , Peng Chen , Martin A. Grepl , Karen Veroy

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…

机器学习 · 统计学 2021-04-21 Tri Dao , Govinda M Kamath , Vasilis Syrgkanis , Lester Mackey

The classical Perceptron algorithm provides a simple and elegant procedure for learning a linear classifier. In each step, the algorithm observes the sample's position and label and updates the current predictor accordingly if it makes a…

机器学习 · 计算机科学 2021-03-24 Saba Ahmadi , Hedyeh Beyhaghi , Avrim Blum , Keziah Naggita

Statistical mechanics is used to study unrealizable generalization in two large feed-forward neural networks with binary weights and output, a perceptron and a tree committee machine. The student is trained by a teacher being larger, i.e.…

凝聚态物理 · 物理学 2007-05-23 Matts Sporre

We examine the supervised learning problem in its continuous setting and give a general optimality condition through techniques of functional analysis and the calculus of variations. This enables us to solve the optimality condition for the…

机器学习 · 计算机科学 2018-07-13 Carlos David Brito Pacheco , Carlos Francisco Brito Loeza

We investigate the learning performance of the pseudolikelihood maximization method for inverse Ising problems. In the teacher-student scenario under the assumption that the teacher's couplings are sparse and the student does not know the…

无序系统与神经网络 · 物理学 2020-08-26 Alia Abbara , Yoshiyuki Kabashima , Tomoyuki Obuchi , Yingying Xu

We consider models of Bayesian inference of signals with vectorial components of finite dimensionality. We show that, under a proper perturbation, these models are replica symmetric in the sense that the overlap matrix concentrates. The…

信息论 · 计算机科学 2020-01-27 Jean Barbier

The binary perceptron is the simplest artificial neural network formed by $N$ input units and one output unit, with the neural states and the synaptic weights all restricted to $\pm 1$ values. The task in the teacher--student scenario is to…

机器学习 · 计算机科学 2019-03-15 Hai-Jun Zhou

Binary perceptron is a fundamental model of supervised learning for the non-convex optimization, which is a root of the popular deep learning. Binary perceptron is able to achieve a classification of random high-dimensional data by…

无序系统与神经网络 · 物理学 2022-04-12 Yang Zhao , Junbin Qiu , Mingshan Xie , Haiping Huang

We consider random instances of non-convex perceptron problems in the high-dimensional limit of a large number of examples $M$ and weights $N$, with finite load $\alpha = M/N$. We develop a formalism based on replica theory to predict the…

无序系统与神经网络 · 物理学 2026-02-11 Elizaveta Demyanenko , Davide Straziota , Carlo Baldassi , Carlo Lucibello

We study learning under a two-step contrastive example oracle, as introduced by Mansouri et. al. (2025), where each queried (or sampled) labeled example is paired with an additional contrastive example of opposite label. While Mansouri et…

The aim of this Lecture Note is to introduce the Signal Processing (SP) community to a powerful yet still under-utilised tool: the semiparametric statistics. In short, the semiparametric framework allows us to estimate or perform hypothesis…

信号处理 · 电气工程与系统科学 2026-05-26 Stefano Fortunati

In theoretical ML, the teacher-student paradigm is often employed as an effective metaphor for real-life tuition. The above scheme proves particularly relevant when the student network is overparameterized as compared to the teacher…

机器学习 · 计算机科学 2023-11-06 Lorenzo Giambagli , Lorenzo Buffoni , Lorenzo Chicchi , Duccio Fanelli

The teacher-student (T/S) learning has been shown to be effective for a variety of problems such as domain adaptation and model compression. One shortcoming of the T/S learning is that a teacher model, not always perfect, sporadically…

机器学习 · 计算机科学 2019-04-30 Zhong Meng , Jinyu Li , Yong Zhao , Yifan Gong

This paper presents a novel online learning method that aims at finding a separator hyperplane between data points labelled as either positive or negative. Since weights and biases of artificial neurons can directly be related to…

机器学习 · 计算机科学 2023-09-13 Ákos Hajnal
‹ 上一页 1 2 3 10 下一页 ›