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.
Transformers predict price movements from limit order books.
New analysis shows transformer models can't learn effectively.
In order to choose a neural network architecture that will be effective for a particular modeling problem, one must understand the limitations imposed by each of the potential options. These limitations are typically described in terms of information theoretic bounds, or by comparing the relative complexity needed to a…
NTK theory fails to predict practical behavior of large-width neural networks.
Study Gaussian-process limits of neural networks using tensor programs.
Proposes a method to improve neural architectures reproducibly.
We introduce a new function-preserving transformation for efficient neural architecture search. This network transformation allows reusing previously trained networks and existing successful architectures that improves sample efficiency. We aim to address the limitation of current network transformation operations that…
This paper develops a new neural network architecture for modeling spatial distributions (i.e., distributions on R^d) which is computationally efficient and specifically designed to take advantage of the spatial structure of limit order books. The new architecture yields a low-dimensional model of price movements deep …
Unified transformer-based LT-TTD improves ranking efficiency and quality.
PASHA optimizes model tuning for large datasets with limited resources.
The existing literature provides evidence that limit order book data can be used to predict short-term price movements in stock markets. This paper proposes a new neural network architecture for predicting return jump arrivals in equity markets with high-frequency limit order book data. This new architecture, based on …
Paper analyzes infinite-width attention layers using Tensor Programs.
In class-incremental learning, a model learns continuously from a sequential data stream in which new classes occur. Existing methods often rely on static architectures that are manually crafted. These methods can be prone to capacity saturation because a neural network's ability to generalize to new concepts is limite…
Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim at finding architectures that optimize the prediction accuracy, these architectures may have complexity and is therefore not suitable being d…
Graph neural networks (GNNs) have emerged recently as a powerful architecture for learning node and graph representations. Standard GNNs have the same expressive power as the Weisfeiler-Leman test of graph isomorphism in terms of distinguishing non-isomorphic graphs. However, it was recently shown that this test cannot…
Tensor programs prove neural network limits for any architecture.
A power-law fit to the empirical inference-compute frontier in LOB prediction suggests a scaling-law-style frontier.
The convolutional layers are core building blocks of neural network architectures. In general, a convolutional filter applies to the entire frequency spectrum of the input data. We explore artificially constraining the frequency spectra of these filters and data, called band-limiting, during training. The frequency dom…
ResNets approximate log-Gaussian at initialization, improving network performance.
New neural network architecture for auction design exploiting permutation symmetry.
The process of designing neural architectures requires expert knowledge and extensive trial and error. While automated architecture search may simplify these requirements, the recurrent neural network (RNN) architectures generated by existing methods are limited in both flexibility and components. We propose a domain-s…
The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS, that generalizes existing weight sharing based NAS approaches. Existing weight shar…
Paper improves deep learning models for limit order book data.
Sensor fusion is a key technology that integrates various sensory inputs to allow for robust decision making in many applications such as autonomous driving and robot control. Deep neural networks have been adopted for sensor fusion in a body of recent studies. Among these, the so-called netgated architecture was propo…
Shared workspace improves neural module coordination in deep learning.
DNArch learns CNN architectures by backpropagation.
Wide stochastic networks show Gaussian behavior and improve training with PAC-Bayesian methods.
Transformer architecture struggles with complex tasks due to limitations in function composition.
This research proves guarantees on sequence models' generalization to longer and novel sequences.
Study improves posterior inference in neural processes with limited data.
Paper optimizes KWS models using NAS and quantization for limited resources.
Machine learning models are vulnerable to adversarial examples: small changes to images can cause computer vision models to make mistakes such as identifying a school bus as an ostrich. However, it is still an open question whether humans are prone to similar mistakes. Here, we address this question by leveraging recen…
We investigate graph neural networks for multi-relational data.
Computer simulations are invaluable tools for scientific discovery. However, accurate simulations are often slow to execute, which limits their applicability to extensive parameter exploration, large-scale data analysis, and uncertainty quantification. A promising route to accelerate simulations by building fast emulat…
FiGS searches over a larger space of architectures for efficient mobile models.
HLOB predicts mid-price changes in L.O.Bs using deep learning.
GNNs generalize CNNs for graph data, showing equivariance and stability.
Neuroscientists classify neurons into different types that perform similar computations at different locations in the visual field. Traditional methods for neural system identification do not capitalize on this separation of 'what' and 'where'. Learning deep convolutional feature spaces that are shared among many neuro…
Recent work has focused on combining kernel methods and deep learning to exploit the best of the two approaches. Here, we introduce a new architecture of neural networks in which we replace the top dense layers of standard convolutional architectures with an approximation of a kernel function by relying on the Nystr{ö}…
Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems. However, their bottlenecks still need to be addressed, and the advantages of multi-scale information and deep architectures have not been sufficiently exploited. In this paper, we theor…
SSNAS finds neural architectures without labeled data.
A new framework generates large hierarchical search spaces for neural architectures.
Optimal transport kernels improve neural architecture search efficiency.
Cell-based NAS search spaces are redundant and lack novelty.
Different neural network (NN) architectures have different advantages. Convolutional neural networks (CNNs) achieved enormous success in computer vision, while recurrent neural networks (RNNs) gained popularity in speech recognition. It is not known which type of NN architecture is the best fit for classification of co…
Deep learning (DL) advances state-of-the-art reinforcement learning (RL), by incorporating deep neural networks in learning representations from the input to RL. However, the conventional deep neural network architecture is limited in learning representations for multi-task RL (MT-RL), as multiple tasks can refer to di…
Unified theory for deep and recurrent networks using Gaussian processes.
Neural network architectures found by sophistic search algorithms achieve strikingly good test performance, surpassing most human-crafted network models by significant margins. Although computationally efficient, their design is often very complex, impairing execution speed. Additionally, finding models outside of the …