A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A new method relaxes molecules without needing non-equilibrium data.
New model outperforms Neural ODEs while being more efficient.
Analyzes how financial network dependencies can lead to multiple equilibrium outcomes and optimal bailout strategies.
New learning algorithm mimics biological neural networks.
Neural network models colloidal particle dynamics in non-equilibrium systems.
Path-independent equilibrium models improve network performance on harder problems.
The paper introduces Robust Correlated Equilibrium for games with time-varying costs and proposes an algorithm to achieve it.
DDEQs extend DEQs to discrete measure inputs using Wasserstein gradient flows.
Study reveals dynamics of neural networks with normalization, weight decay, and SGD.
Proposes a new optimization-based method for aggregating sets in neural networks.
The paper examines Nash equilibrium in GANs for stationary Gaussian processes.
Discovery of atomistic systems with desirable properties is a major challenge in chemistry and material science. Here we introduce a novel, autoregressive, convolutional deep neural network architecture that generates molecular equilibrium structures by sequentially placing atoms in three-dimensional space. The model e…
Deep equilibrium models estimate latent variables from data.
Economic integration, globalization and financial crises represent examples of processes whose understanding requires the analysis of the underlying network structure. Of particular interest is establishing whether a real economic network is in a state of (quasi)stationary equilibrium, i.e. characterized by smooth stru…
This paper studies two important signal processing aspects of equilibrium behavior in non-cooperative games arising in social networks, namely, reinforcement learning and detection of equilibrium play. The first part of the paper presents a reinforcement learning (adaptive filtering) algorithm that facilitates learning…
Neural nets improve plasma equilibrium modeling for NSTX-U.
Deep learning models replicate Kyle's model's market equilibrium.
We perform a geometric study of the equilibrium locus of the flow that models the diffusion process over a circular network of cells. We prove that when considering the set of all possible values of the parameters, the equilibrium locus is a smooth manifold with corners, while for a given value of the parameters, it is…
Wide neural networks converge to Gaussian processes, improving generalization.
Improves GANs training through game theory.
We present a new approach to modeling sequential data: the deep equilibrium model (DEQ). Motivated by an observation that the hidden layers of many existing deep sequence models converge towards some fixed point, we propose the DEQ approach that directly finds these equilibrium points via root-finding. Such a method is…
Computing equilibrium states in condensed-matter many-body systems, such as solvated proteins, is a long-standing challenge. Lacking methods for generating statistically independent equilibrium samples in "one shot", vast computational effort is invested for simulating these system in small steps, e.g., using Molecular…
Generative adversarial networks (GANs) represent a zero-sum game between two machine players, a generator and a discriminator, designed to learn the distribution of data. While GANs have achieved state-of-the-art performance in several benchmark learning tasks, GAN minimax optimization still poses great theoretical and…
New method stabilizes DEQ models by regularizing Jacobian of fixed-point equations.
A major line of contemporary research on complex networks is based on the development of statistical models that specify the local motifs associated with macro-structural properties observed in actual networks. This statistical approach becomes increasingly problematic as network size increases. In the context of curre…
In optimization, the negative gradient of a function denotes the direction of steepest descent. Furthermore, traveling in any direction orthogonal to the gradient maintains the value of the function. In this work, we show that these orthogonal directions that are ignored by gradient descent can be critical in equilibri…
This paper studies how relative performance concerns affect stock prices in a tree-like market model.
Machine learning detects tipping points in complex systems.
New method generates equilibrium glass configurations efficiently.
Recurrent neural networks (RNNs) are particularly well-suited for modeling long-term dependencies in sequential data, but are notoriously hard to train because the error backpropagated in time either vanishes or explodes at an exponential rate. While a number of works attempt to mitigate this effect through gated recur…
Save for some special cases, current training methods for Generative Adversarial Networks (GANs) are at best guaranteed to converge to a `local Nash equilibrium` (LNE). Such LNEs, however, can be arbitrarily far from an actual Nash equilibrium (NE), which implies that there are no guarantees on the quality of the found…
We show that training of generative adversarial network (GAN) may not have good generalization properties; e.g., training may appear successful but the trained distribution may be far from target distribution in standard metrics. However, generalization does occur for a weaker metric called neural net distance. It is a…
DEQs and explicit networks are nearly equivalent for Gaussian mixtures.
This paper provides a general framework for modeling financial contagion in a system with obligations in multiple illiquid assets (e.g., currencies). In so doing, we develop a multi-layered financial network that extends the single network of Eisenberg and Noe (2001). In particular, we develop a financial contagion mod…
Kernel networks' stability edge linked to Fisher Information singularity.
We propose a new equilibrium enforcing method paired with a loss derived from the Wasserstein distance for training auto-encoder based Generative Adversarial Networks. This method balances the generator and discriminator during training. Additionally, it provides a new approximate convergence measure, fast and stable t…
A new method uses deep learning to predict rare events in complex systems.
We represent an exchange economy in terms of statistical ensembles for complex networks by introducing the concept of market configuration. This is defined as a sequence of nonnegative discrete random variables describing the flow of a given commodity from agent to agent . This sequence can be arran…
A key problem in financial mathematics is the forecasting of financial crashes: if we perturb asset prices, will financial institutions fail on a massive scale? This was recently shown to be a computationally intractable (NP-hard) problem. Financial crashes are inherently difficult to predict, even for a regulator whic…
New parameterization of neural networks with Lipschitz bounds for robustness.
New model for recovering unverifiable signals from observers in decentralized networks.
A \emph{new} notion of equilibrium, which we call \emph{strong equilibrium}, is introduced for time-inconsistent stopping problems in continuous time. Compared to the existing notions introduced in ArXiv: 1502.03998 and ArXiv: 1709.05181, which in this paper are called \emph{mild equilibrium} and \emph{weak equilibrium…
EP algorithm improved for CNNs and real-time learning.
Model predicts asset prices from initial shocks using neural networks.
Model shows phase transitions in asset pricing with market maker incentives.
Gradient methods converge exponentially in concave network games.
Two-cycle GEILA equilibria are OLG equilibria and vice versa, with applications to indeterminacy and bubbles.
We prove the existence of a Radner equilibrium in a model with proportional transaction costs on an infinite time horizon and analyze the effect of transaction costs on the endogenously determined interest rate. Two agents receive exogenous, unspanned income and choose between consumption and investing into an annuity.…