English
Related papers

Related papers: Finite size scaling in neural networks

200 papers

We consider gradient-based optimisation of wide, shallow neural networks, where the output of each hidden node is scaled by a positive parameter. The scaling parameters are non-identical, differing from the classical Neural Tangent Kernel…

Machine Learning · Statistics 2025-02-19 Francois Caron , Fadhel Ayed , Paul Jung , Hoil Lee , Juho Lee , Hongseok Yang

We introduce a new combinatorial structure: the superselector. We show that superselectors subsume several important combinatorial structures used in the past few years to solve problems in group testing, compressed sensing, multi-channel…

Data Structures and Algorithms · Computer Science 2010-10-07 Ferdinando Cicalese , Ugo Vaccaro

Using single cluster flip Monte Carlo simulations we accurately determine new finite size scaling functions which are expressed only in terms the variable $x = \xi_L / L$, where $\xi_L$ is the correlation length in a finite system of size…

Condensed Matter · Physics 2009-10-28 Jae-Kwon Kim , Adauto J. F. de Souza\cite{addr} , D. P. Landau

We study finite sample expressivity, i.e., memorization power of ReLU networks. Recent results require $N$ hidden nodes to memorize/interpolate arbitrary $N$ data points. In contrast, by exploiting depth, we show that 3-layer ReLU networks…

Machine Learning · Computer Science 2019-10-30 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

Gardner's analysis of the optimal storage capacity of neural networks is extended to study finite-temperature effects. The typical volume of the space of interactions is calculated for strongly-diluted networks as a function of the storage…

Condensed Matter · Physics 2007-05-23 G. M. Shimi , D. Kim , M. Y. Choi

Learning with an artificial neural network encodes the system behavior in a feed-forward function with a number of parameters optimized by data-driven training. An open question is whether one can minimize the network complexity without…

Statistical Mechanics · Physics 2018-09-03 Dongkyu Kim , Dong-Hee Kim

Neural networks have proven to be extremely powerful tools for modern artificial intelligence applications, but computational and storage complexity remain limiting factors. This paper presents two compatible contributions towards reducing…

Machine Learning · Computer Science 2024-10-30 Sourya Dey , Kuan-Wen Huang , Peter A. Beerel , Keith M. Chugg

We study a simple extended model of oscillator neural networks capable of storing sparsely coded phase patterns, in which information is encoded both in the mean firing rate and in the timing of spikes. Applying the methods of statistical…

Disordered Systems and Neural Networks · Physics 2009-10-31 Masaki Nomura , Toshio Aoyagi

We study the scaling properties of Higgs-Yukawa models. Using the technique of Finite-Size Scaling, we are able to derive scaling functions that describe the observables of the model in the vicinity of a Gaussian fixed point. A feasibility…

High Energy Physics - Lattice · Physics 2016-11-03 David Y. -J. Chu , Karl Jansen , Bastian Knippschild , C. -J. David Lin , Attila Nagy

Cuckoo hashing with a stash is a robust multiple choice hashing scheme with high memory utilization that can be used in many network device applications. Unfortunately, for memory loads beyond 0.5, little is known on its performance. In…

Data Structures and Algorithms · Computer Science 2011-08-10 Yossi Kanizo , David Hay , Isaac Keslassy

We derive the calculation of two critical numbers predicting the behavior of perceptron networks. First, we derive the calculation of what we call the lossless memory (LM) dimension. The LM dimension is a generalization of the…

Neural and Evolutionary Computing · Computer Science 2018-09-11 Gerald Friedland , Mario Krell

Finite-size scaling expressions for the current near the continuous phase transition, and for the local density near the first-order transition, are found in the steady state of the one-dimensional fully asymmetric simple-exclusion process…

Cellular Automata and Lattice Gases · Physics 2009-11-07 Jordan G. Brankov

We give an intuitive geometric explanation for the apparent breakdown of standard finite-size scaling in systems with periodic boundaries above the upper critical dimension. The Ising model and self-avoiding walk are simulated on…

Statistical Mechanics · Physics 2017-03-17 Jens Grimm , Eren Metin Elçi , Zongzheng Zhou , Timothy M. Garoni , Youjin Deng

We propose a ``half'' layer of hidden units that has some of its weights randomly set and some of them trained. A half unit is composed of two stages: First, it takes a weighted sum of its inputs with fixed random weights, and second, the…

Machine Learning · Computer Science 2025-06-06 Ethem Alpaydin

It has been shown in recent years that the stochastic block model (SBM) is sometimes undetectable in the sparse limit, i.e., that no algorithm can identify a partition correlated with the partition used to generate an instance, if the…

The study of the distribution of volumes associated to the internal representations of learning examples allows us to derive the critical learning capacity ($\alpha_c=\frac{16}{\pi} \sqrt{\ln K}$) of large committee machines, to verify the…

Condensed Matter · Physics 2007-05-23 Remi Monasson , Riccardo Zecchina

We propose a novel finite size scaling analysis for percolation transition observed in complex networks. While it is known that cooperative systems in growing networks often undergo an infinite order transition with inverted…

Disordered Systems and Neural Networks · Physics 2013-11-08 Takehisa Hasegawa , Tomoaki Nogawa , Koji Nemoto

According to the concept of typicality, an ensemble average can be accurately approximated by an expectation value with respect to a single pure state drawn at random from a high-dimensional Hilbert space. This random-vector approximation,…

Statistical Mechanics · Physics 2020-05-22 J. Schnack , J. Richter , T. Heitmann , J. Richter , R. Steinigeweg

The ground state and low T behavior of two-dimensional spin systems with discrete binary couplings are subtle but can be analyzed using exact computations of finite volume partition functions. We first apply this approach to Villain's fully…

Disordered Systems and Neural Networks · Physics 2009-11-11 J. Lukic , E. Marinari , O. C. Martin

Empirically-determined scaling laws have been broadly successful in predicting the evolution of large machine learning models with training data and number of parameters. As a consequence, they have been useful for optimizing the allocation…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Katherine L. Mentzer , Andrea Montanari