arXiv subjects

Juyong Song

Publications and source records attributed to Juyong Song.

5 recordsLinked to original sources

arXiv2021

Optimal work extraction and mutual information in a generalized Szilárd engine

A 1929 Gedankenexperiment proposed by Szilárd, often referred to as "Szilárd's engine", has served as a foundation for computing fundamental thermodynamic bounds to information processing. While Szilárd's original box could be partitioned into two halves and contains one gas molecule, we calculate here the maximal average work that can be extracted in a system with $N$ particles and $q$ partitions, given an observer which counts the molecules in each partition, and given a work extraction mechanism that is limited to pressure equalization. We find that the average extracted work is proportional to the mutual information between the one-particle position and the vector containing the counts of how many particles are in each partition. We optimize this quantity over the initial locations of the dividing walls, and find that there exists a critical number of particles $N^{\star}(q)$ below which the extracted work is maximized by a symmetric configuration of the $q$ partitions, and above which the optimal partitioning is asymmetric. Overall, the average extracted work is maximized for a number of particles $\hat{N}(q)<N^{\star}(q)$, with a symmetric partition. We calculate asymptotic values for $N\rightarrow \infty$.

cond-mat.stat-mech↗

arXiv2019

Statistical Criticality arises in Most Informative Representations

We show that statistical criticality, i.e. the occurrence of power law frequency distributions, arises in samples that are maximally informative about the underlying generating process. In order to reach this conclusion, we first identify the frequency with which different outcomes occur in a sample, as the variable carrying useful information on the generative process. The entropy of the frequency, that we call relevance, provides an upper bound to the number of informative bits. This differs from the entropy of the data, that we take as a measure of resolution. Samples that maximise relevance at a given resolution - that we call maximally informative samples - exhibit statistical criticality. In particular, Zipf's law arises at the optimal trade-off between resolution (i.e. compression) and relevance. As a byproduct, we derive a bound of the maximal number of parameters that can be estimated from a dataset, in the absence of prior knowledge on the generative model. Furthermore, we relate criticality to the statistical properties of the representation of the data generating process. We show that, as a consequence of the concentration property of the Asymptotic Equipartition Property, representations that are maximally informative about the data generating process are characterised by an exponential distribution of energy levels. This arises from a principle of minimal entropy, that is conjugate of the maximum entropy principle in statistical mechanics. This explains why statistical criticality requires no parameter fine tuning in maximally informative samples.

physics.data-an↗

arXiv2018

Causality inference in stochastic systems from neurons to currencies: Profiting from small sample size

Success in modeling complex phenomena such as human perception hinges critically on the availability of data and computational power. Significant progress has been made in modeling such phenomena using probabilistic methods, particularly in image analysis and speech recognition. Maximum Likelihood Estimation (MLE) combined with Bayesian model selection is the basis of much of this progress, as MLE converges to the true model with copious data. In the sciences, large enough datasets are rarae aves, so alternatives to MLE must be developed for small sample size. We introduce a data-driven statistical physics approach to model inference based on minimizing a free energy of data and show superior model recovery for small sample sizes. We demonstrate coupling strength inference in non-equilibrium kinetic Ising models, including in the difficult large coupling variability regime, and show scaling to systems of arbitrary size. As applications, we infer a functional connectivity network in the salamander retina and a currency exchange rate network from time-series data of neuronal spiking and currency exchange rates, respectively. Accurate small sample size inference is critical for devising a profitable currency hedging strategy.

physics.data-an↗

arXiv2018

Resolution and Relevance Trade-offs in Deep Learning

Deep learning has been successfully applied to various tasks, but its underlying mechanism remains unclear. Neural networks associate similar inputs in the visible layer to the same state of hidden variables in deep layers. The fraction of inputs that are associated to the same state is a natural measure of similarity and is simply related to the cost in bits required to represent these inputs. The degeneracy of states with the same information cost provides instead a natural measure of noise and is simply related the entropy of the frequency of states, that we call relevance. Representations with minimal noise, at a given level of similarity (resolution), are those that maximise the relevance. A signature of such efficient representations is that frequency distributions follow power laws. We show, in extensive numerical experiments, that deep neural networks extract a hierarchy of efficient representations from data, because they i) achieve low levels of noise (i.e. high relevance) and ii) exhibit power law distributions. We also find that the layer that is most efficient to reliably generate patterns of training data is the one for which relevance and resolution are traded at the same price, which implies that frequency distribution follows Zipf's law.

cs.LG↗

arXiv2015

Minimal Perceptrons for Memorizing Complex Patterns

Feedforward neural networks have been investigated to understand learning and memory, as well as applied to numerous practical problems in pattern classification. It is a rule of thumb that more complex tasks require larger networks. However, the design of optimal network architectures for specific tasks is still an unsolved fundamental problem. In this study, we consider three-layered neural networks for memorizing binary patterns. We developed a new complexity measure of binary patterns, and estimated the minimal network size for memorizing them as a function of their complexity. We formulated the minimal network size for regular, random, and complex patterns. In particular, the minimal size for complex patterns, which are neither ordered nor disordered, was predicted by measuring their Hamming distances from known ordered patterns. Our predictions agreed with simulations based on the back-propagation algorithm.

q-bio.NC↗