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.
Study shows Elo models fail to accurately measure transitive strength in competitive games.
We present a simple model of firm rating evolution. We consider two sources of defaults: individual dynamics of economic development and Potts-like interactions between firms. We show that such a defined model leads to phase transition, which results in collective defaults. The existence of the collective phase depends…
The paper reveals a spinning top geometry in real-world games.
Deep heteroskedastic models overfit, showing a phase transition with regularization strength.
Study of correlated Wigner matrices with BBP transitions.
PLS-SVD struggles with missing data in multimodal datasets, showing a phase transition in performance.
The paper examines how spike strengths and alignments affect overfitting in linear regression models.
In the Information Bottleneck (IB), when tuning the relative strength between compression and prediction terms, how do the two terms behave, and what's their relationship with the dataset and the learned representation? In this paper, we set out to answer these questions by studying multiple phase transitions in the IB…
Continuous phase transitions identified in Doi-Onsager, noisy transformer, and Hegselmann-Krause models.
Combines deep state space models with diffusion models for better forecasting and capturing latent dynamics
A new model separates persistence and transition priors in HDP-HMM.
We study cascades on a two-layer multiplex network, with asymmetric feedback that depends on the coupling strength between the layers. Based on an analytical branching process approximation, we calculate the systemic risk measured by the final fraction of failed nodes on a reference layer. The results are compared with…
Study on signal-plus-noise decomposition in nonlinear spiked random matrices.
We study graph matching with correlated Gaussian features and find thresholds for exact recovery.
GGP models multivariate time series with latent sub-sequences for diverse behaviors.
New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.
RFMs transition from linear to nonlinear under specific input-label correlation.
Zero-sum games such as chess and poker are, abstractly, functions that evaluate pairs of agents, for example labeling them `winner' and `loser'. If the game is approximately transitive, then self-play generates sequences of agents of increasing strength. However, nontransitive games, such as rock-paper-scissors, can ex…
Study nonparametric estimator for Markov chain transition matrices in offline setting.
New insights show stochastic initialization prevents token clustering in deep Transformers.
Generative model learns to mimic time-series behavior to generate accurate trajectories.
Paper explores statistical and computational limits of estimating low-rank Gaussian mixtures.
Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We present two exploration m…
Study on signal recovery from low-rank matrix with sparse noise.
Neural Processes combine the strengths of neural networks and Gaussian processes to achieve both flexible learning and fast prediction in stochastic processes. However, a large class of problems comprises underlying temporal dependency structures in a sequence of stochastic processes that Neural Processes (NP) do not e…
We develop a statistical mechanical approach based on the replica method to study the design space of deep and wide neural networks constrained to meet a large number of training data. Specifically, we analyze the configuration space of the synaptic weights and neurons in the hidden layers in a simple feed-forward perc…
We formulate and analyze a multi-agent model for the evolution of individual and systemic risk in which the local agents interact with each other through a central agent who, in turn, is influenced by the mean field of the local agents. The central agent is stabilized by a bistable potential, the only stabilizing force…
Consistent estimator derived for confounding strength in observational data.
We here present a model of the dynamics of extremism based on opinion dynamics in order to understand the circumstances which favour its emergence and development in large fractions of the general public. Our model is based on the bounded confidence hypothesis and on the evolution of initially anti-conformist agents to…
A new MDP with Bandits approach for sequential decision making in linear-flow scenarios.
More than thirty years ago, Charnes, Cooper and Schinnar (1976) established an enlightening contact between economic production functions (EPFs) -- a cornerstone of neoclassical economics -- and information theory, showing how a generalization of the Cobb-Douglas production function encodes homogeneous functions. As ex…
New gauge fields modify Fokker-Planck dynamics without changing the stationary state.
Random matrix theory explains transient signal detectability in early-stopped gradient flow.
We perform theoretical and algorithmic studies for the problem of clustering and semi-supervised classification on graphs with both pairwise relational information and single-point feature information, upon a joint stochastic block model for generating synthetic graphs with both edges and node features. Asymptotically …
Bayesian model infers strengths from noisy tennis match outcomes.
Understanding tie strength in social networks, and the factors that influence it, have received much attention in a myriad of disciplines for decades. Several models incorporating indicators of tie strength have been proposed and used to quantify relationships in social networks, and a standard set of structural networ…
Novel method uses information theory to measure causal influences during transient neural events.
We present a theoretical analysis of Maximum a Posteriori (MAP) sequence estimation for binary symmetric hidden Markov processes. We reduce the MAP estimation to the energy minimization of an appropriately defined Ising spin model, and focus on the performance of MAP as characterized by its accuracy and the number of s…
This paper calculates interaction strength for translation surfaces with multiple singularities.
Develops a more flexible HDP-HMM for temporal data segmentation.
Consider a two-class clustering problem where we observe , , . The feature vector is unknown but is presumably sparse. The class labels are also unknown and the main interest is to estimate them. We are interested …
The optimization of a large random portfolio under the Expected Shortfall risk measure with an regularizer is carried out by analytical calculation. The regularizer reins in the large sample fluctuations and the concomitant divergent estimation error, and eliminates the phase transition where this error would …
Synaptic strength can be seen as probability to propagate impulse, and according to synaptic plasticity, function could exist from propagation activity to synaptic strength. If the function satisfies constraints such as continuity and monotonicity, neural network under external stimulus will always go to fixed point, a…
A new method uses randomized trials to estimate the strength of unobserved confounding.
SGD quickly learns a spurious XOR feature before the signal feature, revealing learning dynamics.
Convolutional Neural Networks(CNNs) are both computation and memory intensive which hindered their deployment in mobile devices. Inspired by the relevant concept in neural science literature, we propose Synaptic Pruning: a data-driven method to prune connections between input and output feature maps with a newly propos…
In this work, we perform an exploratory study on synthesizing deep neural networks using biological synaptic strength distributions, and the potential influence of different distributions on modelling performance particularly for the scenario associated with small data sets. Surprisingly, a CNN with convolutional layer…
Even before deep learning architectures became the de facto models for complex computer vision tasks, the softmax function was, given its elegant properties, already used to analyze the predictions of feedforward neural networks. Nowadays, the output of the softmax function is also commonly used to assess the strength …