arXiv research

Study shows wealth distribution tails near criticality are not universal.

Paper tackles overestimation bias in continuous control, improving performance by 25%.

We provide evidence that cumulative distributions of absolute normalized returns for the $100$ American companies with the highest market capitalization, uncover a critical behavior for different time scales $Δt$. Such cumulative distributions, in accordance with a variety of complex --and financial-- systems, can be m…

Study shows flash crashes in finance are self-organized criticality events.

New method selects critical DER scenarios for distribution grid investment planning.

In this paper, we propose a distributed off-policy actor critic method to solve multi-agent reinforcement learning problems. Specifically, we assume that all agents keep local estimates of the global optimal policy parameter and update their local value function estimates independently. Then, we introduce an additional…

Critical graphs of quadratic differentials equidistribute in moduli space.

Urban transformations within large and growing metropolitan areas often generate critical dynamics affecting social interactions, transport connectivity and income flow distribution. We develop a statistical-mechanical model of urban transformations, exemplified for Greater Sydney, and derive a thermodynamic descriptio…

We give an asymptotic probabilistic real Riemann-Hurwitz formula computing the expected real ramification index of a random covering over the Riemann sphere. More generally, we study the asymptotic expected number and distribution of critical points of a random real Lefschetz pencil over a smooth real algebraic variety…

The z-transform technique is used to investigate the model for distribution of high-tax payers, which is proposed by two of the authors (K. Y and S. M) and others. Our analysis shows an asymptotic power-law of this model with the exponent -5/2 when a total ``mass'' has a certain critical value. Below the critical value…

Neural networks trained with actor-critic algorithms converge to ODEs under weak convergence analysis.

Learning the distribution of natural images is one of the hardest and most important problems in machine learning. The problem remains open, because the enormous complexity of the structures in natural images spans all length scales. We break down the complexity of the problem and show that the hierarchy of structures …

This work aims to create a large-scale model for critical care time series data.

We study a simplification of GAN training: the problem of transporting particles from a source to a target distribution. Starting from the Sobolev GAN critic, part of the gradient regularized GAN family, we show a strong relation with Optimal Transport (OT). Specifically with the less popular dynamic formulation of OT …

This paper studies the critical dynamics of random surfaces, focusing on area and genus evolution.

The increasing quantity of PV generation connected to distribution networks is creating challenges in maintaining and controlling voltages in those distribution networks. Determining the maximum hosting capacity for new PV installations based on the historical data is an essential task for distribution networks. Analyz…

IDAC improves reinforcement learning efficiency by modeling implicit distributions.

Improves RL generalization by minimizing adversarial risk.

We analyze critical points of the Sliced Wasserstein Distance for optimization stability.

In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…

The aim here is to study the concept of pairing multifractality between time series possessing non-Gaussian distributions. The increasing number of rare events creates "criticality". We show how the pairing between two series is affected by rare events, which we call "coupled criticality". A method is proposed for stud…

Critical learning periods found in deep linear networks too.

Deep learning depends on tuning layers near critical points.

A simple model economy with locally interacting producers and consumers is introduced. When driven by extremal dynamics, the model self-organizes {\em not} to an attractor state, but to an asymptote, on which the economy has a constant rate of deflation, is critical, and exhibits avalanches of activity with power-law d…

Actor-critic algorithms converge to an ODE as data samples change dynamically.

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($π$) and the behavior policy (b) is a major cause of instability. High variance also originates from distributional mismatch. The var…

A framework identifies worst-case decision points in safety-critical scenarios, improving risk assessment by 10 hours.

We identify a fundamental problem in policy gradient-based methods in continuous control. As policy gradient methods require the agent's underlying probability distribution, they limit policy representation to parametric distribution classes. We show that optimizing over such sets results in local movement in the actio…

This paper considers a distributed reinforcement learning problem in which a network of multiple agents aim to cooperatively maximize the globally averaged return through communication with only local neighbors. A randomized communication-efficient multi-agent actor-critic algorithm is proposed for possibly unidirectio…

We consider a $(2q+1)$-dimensional smooth manifold $M$ equipped with a $(q+1)$-dimensional, a priori non-integrable, distribution ${\cal D}$ and a $q$-vector field ${\bf T}=T_1\wedge\ldots\wedge T_q$, where $\{T_i\}$ are linearly independent vector fields transverse to~${\cal D}$. Using a $q$-form $ω$ such that ${\cal …

Stock markets are complex systems exhibiting collective phenomena and particular features such as synchronization, fluctuations distributed as power-laws, non-random structures and similarity to neural networks. Such specific properties suggest that markets operate at a very special point. Financial markets are believe…

The paper explores how topological methods can reveal insights into electric charge distributions on knots.

We have numerically simulated the ideal-gas models of trading markets, where each agent is identified with a gas molecule and each trading as an elastic or money-conserving two-body collision. Unlike in the ideal gas, we introduce (quenched) saving propensity of the agents, distributed widely between the agents ($0 \le…

The paper analyzes how SGD visits different regions of a non-convex problem's state space.

We examine the total mixed scalar curvature of a fixed distribution as a functional of a pseudo-Riemannian metric. We develop variational formulas for quantities of extrinsic geometry of the distribution to find the critical points of this action. Together with the arbitrary variations of the metric, we consider also v…

MODULE solves LfO problem with high sample efficiency and stability.

A new method improves actor-critic RL by integrating HMC, enhancing policy distribution and exploration.

The paper introduces a novel method for training neural network Stein critics with staged $L^2$-regularization.

Evaluation and validation of complicated control systems are crucial to guarantee usability and safety. Usually, failure happens in some very rarely encountered situations, but once triggered, the consequence is disastrous. Accelerated Evaluation is a methodology that efficiently tests those rarely-occurring yet critic…

Critical volatility triggers log-normal to power-law transitions in interconnected systems.

A new framework for measuring uncertainty in machine learning models.

The paper evaluates variational auto-encoders using model criticism methods.

The paper explores multidimensional critic output in GANs, improving convergence and diversity.

Deep actor-critic learning optimizes power control in mobile networks.

We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from its local task only, but it aims to learn a policy that performs well on average …

DAC enhances exploration in reinforcement learning with entropy regularization.

Stochastic regularisation is an important weapon in the arsenal of a deep learning practitioner. However, despite recent theoretical advances, our understanding of how noise influences signal propagation in deep neural networks remains limited. By extending recent work based on mean field theory, we develop a new frame…

Parastatistic distribution of a total debt owed to a large number of creditors considered in relation to the duration of these debts. The process of debt calculation depends on the fractal dimension of economic system in which this process takes place. Two actual variants of these dimensions are investigated. Critical …