We develop a second-order model for limit order books in a single scaling regime.
problem Modeling price and volume dynamics in a limit order book with market and limit orders at a common time scale.
method Established a first- and second-order approximation for an infinite dimensional limit order book model.
result Proved the existence and uniqueness of a solution for the second-order approximation.
This paper proposes a multi-scale Markov-Switching GARCH model for EUR/USD volatility.
problem Non-stationary financial volatility requires models that capture changing market conditions across multiple timescales.
method Triple-timeframe Markov-Switching GARCH (MS-GARCH) framework with AR(1)-MS-GARCH models and TVTP for short horizons.
result The proposed model produces statistically distinct regimes and superior volatility forecasting performance.
The paper analyzes SGD in high-dimensional networks, revealing new scaling limits.
problem Understanding SGD dynamics in high-dimensional networks.
method Analyzing the effective dynamics of SGD using recent work on the subject.
result A new correction term emerges at the critical scaling regime, changing the phase diagram.
Ensembles of random-feature models can't outperform a single large model.
problem Finding the optimal balance between model size and ensemble size.
method Deterministic equivalent risk estimates and scaling laws analysis.
result Ensembles of random-feature models achieve near-optimal performance only under specific conditions.
New algorithm learns switching dynamics from multiple neural signals.
problem Learning accurate switching dynamical system models from multimodal neural data.
method Unsupervised learning algorithm for multiscale switching dynamical system models.
result Switching multiscale dynamical system models outperform single-scale models in behavior decoding.
Sharp feature transitions revealed in extensive-width networks.
problem Learning hierarchical features from noisy queries in large networks.
method Information-theoretic analysis and heuristic decoupling argument.
result Sequential phase transitions in feature learnability and effective width.
In order to obtain a reasonable and reliable forecast method for crude oil price volatility, this paper evaluates the forecast performance of single-regime GARCH models (including the standard linear GARCH model and the nonlinear GJR-GARCH and EGARCH models) and the two-regime Markov Regime Switching GARCH (MRS-GARCH) …
Superstatistics is a widely employed tool of non-equilibrium statistical physics which plays an important role in analysis of hierarchical complex dynamical systems. Yet, its "canonical" formulation in terms of a single nuisance parameter is often too restrictive when applied to complex empirical data. Here we show tha…
Paper analyzes infinite-width attention layers using Tensor Programs.
problem Capturing the infinite-width limit of attention layers.
method Tensor Programs framework to rigorously identify the limit distribution.
result Derives exact form of infinite-width limit distribution without Gaussian approximations.
Embedded ensembles improve neural network performance efficiently.
problem Improving neural network performance with fewer resources.
method Analyzing the wide network limit of gradient descent dynamics using Neural-Tangent-Kernel.
result Embedded ensembles exhibit two regimes: independent and collective, affecting performance.
Three training regimes found for scale-invariant neural networks on the sphere.
problem Training scale-invariant neural networks on the sphere with varying effective learning rate.
method Investigated three regimes of training: convergence, chaotic equilibrium, and divergence.
result Discovered three distinct training regimes with unique characteristics.
We study the effect of liquidity freezes on an economic agent optimizing her utility of consumption in a perturbed Black-Scholes-Merton model. The single risky asset follows a geometric Brownian motion but is subject to liquidity shocks, during which no trading is possible and stock dynamics are modified. The liquidity…
Study uncovers scaling laws and spectral properties of shallow neural networks.
problem Understanding scaling laws and spectral properties of shallow neural networks.
method Leveraging connections with matrix compressed sensing and LASSO, derived a phase diagram for excess risk.
result Uncovered crossovers between scaling regimes and plateau behaviors, validated empirical observations.
We investigate multifractality in the Korean stock-market index KOSPI. The generalized qth order height-height correlation function shows multiscaling properties. There are two scaling regimes with a crossover time around tc=40 min. We consider the original data sets and the modified data sets obtained by removin…
The paper analyzes the dynamics of tokens in transformer models at moderate interaction levels.
problem Understanding the evolution of tokens in transformer models at moderate interaction levels.
method Modeling transformer models as a system of particles interacting in a mean-field way and studying the corresponding dynamics.
result Characterization and convergence of the limiting dynamics in different phases of the system.
New framework for regression trees with multivariate response and dynamic mean vectors.
problem Characterizing and implementing regression trees for multivariate responses.
method High dimensional model with dynamic mean vectors over multi-dimensional change axes.
result Optimal rate of convergence and asymptotic valid confidence intervals for change points.
Theory explains neural network scaling with dataset and model size.
problem Neural network scaling laws with dataset and model size.
method Identified variance-limited and resolution-limited scaling behaviors.
result Four scaling regimes explained: infinite data, infinite width, resolution-limited, and large width.
High-dimensional shrinkage risk depends on the default prior for the common scale.
problem Choosing the default prior for the common scale in high-dimensional shrinkage.
method Using radial-power benchmark to compare variance-flat and standard deviation-flat priors.
result The standard deviation-flat prior has a one-unit asymptotic risk advantage near the origin.
New method improves Bayesian model selection for neural dynamics.
problem Bayesian methods struggle with large datasets and computational constraints.
method Computation-Aware State-Space Model (CASSM) with model selection.
result CASSM yields competitive performance and improved uncertainty calibration.
Develops a new model to better predict corporate bond yields.
problem Persistent shifts in interest rates undermine single-regime models.
method Regime-switching generalized CIR model with two-state short-rate process and credit factors.
result The model improves joint curve fit and delivers interpretable probabilities.
Paper proposes a new framework to compare trading strategies by accounting for market conditions.
problem Lack of information on how trading strategy performance varies with market conditions.
method Uses a GAMLSS/ZAGA framework to model the Adjusted Information Ratio (IR∗) for a SVMP and BH strategy across 146 folds of the S&P 500. result Dominance of SVMP over BH is conditional on market regime, as shown by differences in expected IR∗ and its variance. We discuss the approximation of the value function for infinite-horizon discounted Markov Reward Processes (MRP) with nonlinear functions trained with the Temporal-Difference (TD) learning algorithm. We first consider this problem under a certain scaling of the approximating function, leading to a regime called lazy tr…
New scaling framework for MoE architectures ensures stability and optimal performance at scale.
problem Lack of principled understanding of how hyperparameters should scale in MoE architectures.
method Developed a novel Dynamical Mean Field Theory (DMFT) for three scaling regimes of MoE architectures.
result Derived Maximally Scale-Stable Parameterization (MSSP) for SGD and Adam, providing robust learning rate transfer and monotonic improvement with scale.
Large learning rates work surprisingly well in standard parameterization, contrary to theory.
problem Theoretical limits of large learning rates do not match practical network behavior.
method Fine-grained analysis of learning rates and network behavior under cross-entropy loss.
result There are two distinct sub-regimes of unstable learning rates, with a controlled divergence regime where features continue to evolve.
CAIRO separates ranking from scaling to improve robustness.
problem Conflating ranking and scaling in regression leads to model vulnerability.
method Two-stage approach: first learns a scoring function, then recovers scale.
result CAIRO recovers true regression function with auto-calibration guarantees.
Data pruning algorithms struggle in high compression regimes, as shown by theoretical and empirical studies.
problem Limitations of score-based data pruning algorithms in high compression regimes.
method Theoretical and empirical analysis of score-based data pruning algorithms.
result Score-based data pruning algorithms fail in high compression regimes due to 'No Free Lunch' theorems.
Study shows optimal model performance at critical level of feature learning.
problem Catastrophic forgetting in neural networks, especially in non-stationary environments.
method Systematic study on model scale and feature learning, using dynamical mean field theory.
result Optimal performance achieved at a critical level of feature learning, dependent on task non-stationarity and model scale.
The paper studies learning dynamics in two-layer neural networks.
problem Learning dynamics and time scales in two-layer neural networks.
method Gradient flow dynamics of a wide two-layer neural network in high-dimension, with data following a single-index model.
result The learning dynamics exhibit separation of timescales and intermittency.
ElbowSig assesses clustering structure at multiple scales.
problem Selecting optimal number of clusters in unsupervised learning.
method Formalizes elbow heuristic with a normalized discrete curvature statistic.
result Validates multiscale clustering structure over various resolutions.
When can reliable inference be drawn in the "Big Data" context? This paper presents a framework for answering this fundamental question in the context of correlation mining, with implications for general large scale inference. In large scale data applications like genomics, connectomics, and eco-informatics the dataset…
Financial markets provide an ideal frame for the study of crossing or first-passage time events of non-Gaussian correlated dynamics mainly because large data sets are available. Tick-by-tick data of six futures markets are herein considered resulting in fat tailed first-passage time probabilities. The scaling of the re…
Optimal data splitting improves covariance matrix estimation in large datasets.
problem Improving large covariance matrix estimation in high-dimensional settings.
method Focus on holdout method, derive closed-form error expression, connect to eigenvalue variance.
result Optimal train-test split scales as square root of matrix dimension.
Model shows feature learning can improve neural scaling laws for hard tasks.
problem Understanding and improving neural network scaling laws for various task difficulties.
method Developed a solvable model of neural scaling laws, identified three scaling regimes, and demonstrated feature learning's impact on scaling exponents.
result Feature learning can improve scaling with training time and compute for hard tasks, nearly doubling the exponent.
DeRegiME forecasts with regime structure, improving probabilistic predictions across various time series.
problem Probabilistic forecasting discards residual uncertainty, and distribution shifts are hard to capture.
method DeRegiME uses a sparse variational Gaussian process with a nonstationary regime-mixing kernel to separate latent uncertainty regimes.
result DeRegiME improves NLPD by 20.3% on average across benchmarks, with gains on CRPS and MSE.
Framework models multiscale dynamics with Bayesian learning for regime changes.
problem Analyzing complex interactions between fast and slow processes.
method Hierarchical state-space modeling with Sequential Monte Carlo.
result Bayesian approach accurately tracks state transitions and identifies switching dynamics.
Empirical analysis of financial market trends and reversions across various time scales.
problem Understanding trends and reversions in financial markets over different time scales.
method Analysis of 14 years of futures tick data, 30 years of daily futures prices, 330 years of monthly asset prices, and yearly financial data since medieval times.
result Markets exhibit trending and reversion regimes with different time scales, explaining trends persistence and reversions.
Study how generalization scales with model size and data in quadratic neural networks.
problem Understanding how generalization scales with model size and data in quadratic neural networks.
method Analyzed ℓ2-regularized empirical test error minimization in a quadratic two-layer network with finite-sample setting and structured data. result Revealed a phase diagram with distinct scaling regimes as the number of parameters varies, showing data-dependent power laws controlled by spectral structure of the target.
A new method for efficiently updating large-scale matrices in real-time.
problem Updating large-scale matrices with evolving data in real-time.
method Incremental SVD approach that handles row/column appends, rank-1 updates, and refresh strategies.
result Incremental SVD achieves accuracy close to full SVD with a fraction of the computational cost.
Two distinct limits for deep learning have been derived as the network width h→∞, depending on how the weights of the last layer scale with h. In the Neural Tangent Kernel (NTK) limit, the dynamics becomes linear in the weights and is described by a frozen kernel Θ. By contrast, in the Mean-Field …
On the fifth of February, 2018, the Dow Jones Industrial Average dropped 1,175.21 points, the largest single-day fall in history in raw point terms. This followed a 666-point loss on the second, and another drop of over a thousand points occurred three days later. It is natural to ask whether these events indicate a tr…
MAP-Elites generates diverse trading strategies for improved execution performance.
problem Optimizing trading execution schedules in volatile market conditions.
method Quality-diversity algorithm (MAP-Elites) generating a portfolio of specialized strategies.
result Diverse strategies achieve 8-10% performance improvements, validating quality-diversity methods.
In this paper mechanisms of reversion - momentum transition are considered. Two basic nonlinear mechanisms are highlighted: a slow and fast bifurcation. A slow bifurcation leads to the equilibrium evolution, preceded by stability loss delay of a control parameter. A single order parameter is introduced by Markovian cha…
Study on how initialization scale affects neural network training regimes.
problem Understanding the transition between kernel and rich regimes in overparametrized models.
method Analysis of simple depth-D models and empirical testing on complex models.
result Scale of initialization controls transition between kernel and rich regimes.
Hybrid model improves synthetic equity data generation.
problem Generating realistic synthetic financial time series.
method Discretized excess growth rates into states with Poisson jumps, estimating parameters directly.
result Framework achieved high pass rates for distributional and volatility clustering tests.
Model shows loss curve with two distinct exponents due to sparse activations.
problem Sparse activations impact neural network scaling laws.
method Introduced a model for neural scaling laws under sparse activations, derived asymptotic population loss, and analyzed gradient-descent dynamics.
result Loss curve exhibits double-descent peak near interpolation threshold with two distinct scaling exponents.
New insights into SGD and SGD-M in high dimensions.
problem Understanding and comparing SGD and SGD-M in high-dimensional settings.
method Developed high-dimensional scaling limits for SGD-M and online SGD, examining their dynamics and performance.
result SGD-M amplifies high-dimensional effects, potentially degrading performance compared to online SGD.
In a recent paper [\textit{M. Cristelli, A. Zaccaria and L. Pietronero, Phys. Rev. E 85, 066108 (2012)}], Cristelli \textit{et al.} analysed relation between skewness and kurtosis for complex dynamical systems and identified two power-law regimes of non-Gaussianity, one of which scales with an exponent of 2 and the oth…
Investigates stochastic networks on disordered lattices, converging to Brownian web in 2D.
problem Stochastic networks on disordered lattices.
method Directed spanning forests on randomly perturbed lattices.
result DSF converges to Brownian web in 2D under diffusive scaling.