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.
Finet uses FBN for efficient, lightweight neural networks.
Reinforcement learning improves portfolio optimization, but state normalization affects performance.
This study improves state estimation for nonlinear systems using conditional normalizing flows.
Optimal transport theory applied to quantum states on Grassmannians.
Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute…
In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with respect to their depth in the network. Our proposed normalization and decay techniques…
Normalization layers are a staple in state-of-the-art deep neural network architectures. They are widely believed to stabilize training, enable higher learning rate, accelerate convergence and improve generalization, though the reason for their effectiveness is still an active research topic. In this work, we challenge…
New method trains deep ResNets without normalization, achieving state-of-the-art performance.
We find a normal form for two-input flat discrete-time systems.
FORBES learns flexible belief states for POMDPs using normalizing flows.
Spin-glasses are universal models that can capture complex behavior of many-body systems at the interface of statistical physics and computer science including discrete optimization, inference in graphical models, and automated reasoning. Computing the underlying structure and dynamics of such complex systems is extrem…
Batch normalization has become ubiquitous in many state-of-the-art nets. It accelerates training and yields good performance results. However, there are various other alternatives to normalization, e.g. orthonormalization. The objective of this paper is to explore the possible alternatives to channel normalization with…
We propose a simple but effective multi-source domain generalization technique based on deep neural networks by incorporating optimized normalization layers that are specific to individual domains. Our approach employs multiple normalization methods while learning separate affine parameters per domain. For each domain,…
The article constructs Feynman propagators for normally hyperbolic operators on curved spacetimes.
The policy gradient theorem is defined based on an objective with respect to the initial distribution over states. In the discounted case, this results in policies that are optimal for one distribution over initial states, but may not be uniformly optimal for others, no matter where the agent starts from. Furthermore, …
Optimal search for change point anomaly in multiple processes.
Detects anomalies in multiple processes using hidden Markov models.
We describe a normal surface algorithm that decides whether a knot, with known degree of the colored Jones polynomial, satisfies the Strong Slope Conjecture. We also discuss possible simplifications of our algorithm and state related open questions. We establish a relation between the Jones period of a knot and the num…
Fine-tuning normalization layers can reconstruct smaller networks.
Local bifurcation theory typically deals with the response of a degenerate but isolated equilibrium state or periodic orbit of a dynamical system to perturbations controlled by one or more independent parameters, and characteristically uses tools from singularity theory. There are many situations, however, in which the…
In this paper, we introduce a new sparsity-promoting prior, namely, the "normal product" prior, and develop an efficient algorithm for sparse signal recovery under the Bayesian framework. The normal product distribution is the distribution of a product of two normally distributed variables with zero means and possibly …
TaskNorm improves meta-learning performance by rethinking batch normalization.
Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution lear…
We introduce graph normalizing flows: a new, reversible graph neural network model for prediction and generation. On supervised tasks, graph normalizing flows perform similarly to message passing neural networks, but at a significantly reduced memory footprint, allowing them to scale to larger graphs. In the unsupervis…
We study the dependence structure of market states by estimating empirical pairwise copulas of daily stock returns. We consider both original returns, which exhibit time-varying trends and volatilities, as well as locally normalized ones, where the non-stationarity has been removed. The empirical pairwise copula for ea…
RC flow learns molecular kinetics in low dimensions.
New ODE-Block handles stateful layers with continuous-in-depth functions using basis functions.
We present a modern formulation of Élie Cartan's structure theory for Lie pseudogroups and prove a reduction theorem that clarifies the role of Cartan's systatic system. The paper is divided into three parts. In part one, using notions coming from the theory of Lie groupoids and algebroids, we introduce the framework o…
ETGPSSM efficiently models high-dimensional, non-stationary systems with reduced complexity.
The paper proves convergence of normalized Ricci flow on compact manifolds.
The paper proposes deep normalization to improve speaker recognition performance.
Proposes a method to detect anomalies in multi-subgroup normal data.
The object of this article is to compute the holonomy group of the normal connection of complex parallel submanifolds of the complex projective space. We also give a new proof of the classification of complex parallel submanifolds by using a normal holonomy approach. Indeed, we explain how these submanifolds can be reg…
Very deep CNNs achieve state-of-the-art results in both computer vision and speech recognition, but are difficult to train. The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN). Inspired by Self- Normalizing Neural Networks, we propose the self-normaliz…
CFIL uses coupled flows to model state distributions for imitation learning.
In this paper we introduce the fourth fundamental form for the hypersurfaces in and the space-like hypersurfaces in and discuss the conformality of the normal Gauss maps of the hypersurfaces in and . Particularly, we discuss the surfaces with conformal normal Gauss maps in…
Proposes a new model for time series that considers smooth transitions between states.
The paper defines -normality for contact and paracontact manifolds and explores their properties.
Proposes a unified normalization method for multi-domain medical images.
Proof of existence for ideal triangulations that normalize fibers in certain 3-manifolds.
In this paper we study the main geometric properties of the Carnot-Carathéodory (abbreviated CC) distance $\dc$ in the setting of -step sub-Riemannian Carnot groups from many different points of view. An extensive study of the so-called normal CC-geodesics is given. We state and prove some related variational formul…
Proposes differentially private normalizing flows for privacy-preserving density estimation.
We develop a diagrammatic formalism for calculating the Alexander polynomial of the closure of a braid as a state-sum. Our main tools are the Markov trace formulas for the HOMFLY-PT polynomial and Young's semi-normal representations of the Iwahori-Hecke algebras of type A.
The study identifies and analyzes different market regimes in equity markets using advanced signal processing techniques.
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One problem with this approach is that the anomaly score of rare-normal sounds becomes hig…
Graphical normalizing flows use Bayesian networks to improve normalizing flows' interpretability and performance.
Optimizes recommendation models using skew normal distribution.
Layer normalization (LayerNorm) is a technique to normalize the distributions of intermediate layers. It enables smoother gradients, faster training, and better generalization accuracy. However, it is still unclear where the effectiveness stems from. In this paper, our main contribution is to take a step further in und…