arXiv research

Unified theory for neural scaling laws in hierarchically compositional data.

A hierarchical model shows how scaling laws emerge from sequential feature recovery.

The paper solves a problem in constructing a bicategory of algebra bundles.

The study finds that the export shares of machinery and food/crude materials are significantly correlated with GDP.

The relaxation dynamics of aftershocks after large volatility shocks are investigated based on two high-frequency data sets of the Shanghai Stock Exchange Composite (SSEC) index. Compared with previous relevant work, we have defined main financial shocks based on large volatilities rather than large crashes. We find th…

Algorithmic fairness, and in particular the fairness of scoring and classification algorithms, has become a topic of increasing social concern and has recently witnessed an explosion of research in theoretical computer science, machine learning, statistics, the social sciences, and law. Much of the literature considers…

A formulation for a non-trivial composition of two classical gauge structures is given: Two parent gauge structures of a common base space are synthesized so as to obtain a daughter structure which is fundamental by itself. The model is based on a pair of related connections that take their values in the product space …

Dynamic risk measures follow law invariance principles over time.

We utilize a recently developed genetic algorithm, in conjunction with discrete wavelets, for carrying out successful forecasts of the trend in financial time series, that includes the NASDAQ composite index. Discrete wavelets isolate the local, small scale variations in these non-stationary time series, after which th…

We introduce a new statistical tool (the TP-statistic and TE-statistic) designed specifically to compare the behavior of the sample tail of distributions with power-law and exponential tails as a function of the lower threshold u. One important property of these statistics is that they converge to zero for power laws o…

In the double field theory, gauge symmetries are realized as generalized diffeomorphisms in the doubled spacetime. By consistency of the theory, dependence of tensor fields on the doubled coordinates is strongly constrained. This causes finite transformation law highly complicated, both technically and conceptually. In…

Researchers study how skills are learned in neural networks using physics principles.

We propose a unified modelling framework that theoretically justifies the main empirical regularities characterizing the international trade network. Each country is associated to a Polya urn whose composition controls the propensity of the country to trade with other countries. The urn composition is updated through t…

The concept of a symplectic structure first appeared in the works of Lagrange on the so-called "method of variation of the constants". These works are presented, together with those of Poisson, who first defined the composition law called today the "Poisson bracket". The method of variation of the constants is presente…

The paper defines a category of Lagrangian correspondences in super Hilbert spaces and constructs a functorial field theory.

Inverse depth scaling found in LLMs due to similar layers averaging error.

In this paper, we studied the dynamics of the log-return distribution of the Korean Composition Stock Price Index (KOSPI) from 1992 to 2004. Based on the microscopic spin model, we found that while the index during the late 1990s showed a power-law distribution, the distribution in the early 2000s was exponential. This…

The paper extends properties of smooth functions to closed sets and maps.

Optimizes quickest change detection with bounded means under ARL constraint.

This paper shows how to construct sequential tests with power one against weakly compact sets in Polish spaces.

Study reveals a universal formula for knotting in random equilateral polygons.

A large consensus now seems to take for granted that the distributions of empirical returns of financial time series are regularly varying, with a tail exponent close to 3. We revisit this results and use standard tests as well as develop a battery of new non-parametric and parametric tests (in particular with stretche…

We derive a system of stochastic differential equations simulating the dynamics of the three agent groups with herding interaction. Proposed approach can be valuable in the modeling of the complex socio-economic systems with similar composition of the agents. We demonstrate how the sophisticated statistical features of…

Modular neural networks generalize better with less data.

The work focuses upon the relativistic and geometric properties of the space--time endowed tentatively with the metric function of the Berwald--Moor type. The zero curvature of indicatrix is a remarkable property of the approach. We demonstrate how the associated geodesic equations can be solved in a transparent way, t…

The seemingly infinite diversity of the natural world arises from a relatively small set of coherent rules, such as the laws of physics or chemistry. We conjecture that these rules give rise to regularities that can be discovered through primarily unsupervised experiences and represented as abstract concepts. If such r…

DNNs can learn complex functions efficiently by breaking the curse of dimensionality.

We introduce a novel approach, requiring only mild assumptions, for the characterization of deep neural networks at initialization. Our approach applies both to fully-connected and convolutional networks and easily incorporates batch normalization and skip-connections. Our key insight is to consider the evolution with …

This paper reviews deep learning techniques for face recognition and sketch matching.

We present a simple transformation of the formulation of the log-periodic power law formula of the Johansen-Ledoit-Sornette model of financial bubbles that reduces it to a function of only three nonlinear parameters. The transformation significantly decreases the complexity of the fitting procedure and improves its sta…

New framework resolves central limit behavior in differential privacy.

This work is an analytical and numerical study of the composition of several fractals into one and of the relation between the composite dimension and the dimensions of the component fractals. In the case of composition of standard IFS with segments of equal size, the composite dimension can be expressed as a function …

We prove the exponential law $\mathcal A(E \times F, G) \cong \mathcal A(E,\mathcal A(F,G))$ (bornological isomorphism) for the following classes $\mathcal A$ of test functions: $\mathcal B$ (globally bounded derivatives), $W^{\infty,p}$ (globally $p$-integrable derivatives), $\mathcal S$ (Schwartz space), $\mathcal D$…

New geometric approach for analyzing compositional data like gut microbiomes.

We consider the effects of the global financial crisis through a local Korean financial market around the 2008 crisis. We analyze 185 individual stock prices belonging to the KOSPI (Korea Composite Stock Price Index), cosidering three time periods: the time before, during, and after the crisis. The complex networks gen…

Study on deep neural networks using branching processes and Mehler's formula.

We establish conditions for compositional generalization in machine learning.

This paper proves hyperbolicity of virtual knot compositions.

Develops methods for causal inference in compositional data using instrumental variables.

In classical field theory, the composite fibred manifolds Y -> Z -> X provides the adequate mathematical formulation of gauge models with broken symmetries, e.g., the gauge gravitation theory. This work is devoted to connections on composite fibred manifolds. In particular, we get the horizontal splitting of the vertic…

This paper compares two different frameworks recently introduced in the literature for measuring risk in a multi-period setting. The first corresponds to applying a single coherent risk measure to the cumulative future costs, while the second involves applying a composition of one-step coherent risk mappings. We summar…

The p-index improves investment performance for NYSE stocks but not for SSE stocks.

In finance, one usually deals not with prices but with growth rates $R$, defined as the difference in logarithm between two consecutive prices. Here we consider not the trading volume, but rather the volume growth rate $\tilde R$, the difference in logarithm between two consecutive values of trading volume. To this end…

Model predicts composite structures assembly quality with input uncertainty.

New algorithm reduces complexity for optimizing complex machine learning tasks.

This paper introduces compositional data analysis for financial ratios, improving industry-level analysis.

Study challenges neural models in compositional learning tasks.

Constructs unbounded Kasparov product for sphere embeddings into Euclidean space.