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.
Model combines long-term and short-term memory using conceptors.
We propose a new data-driven method to select the optimal number of relevant components in Principal Component Analysis (PCA). This new method applies to correlation matrices whose time autocorrelation function decays more slowly than an exponential, giving rise to long memory effects. In comparison with other availabl…
We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in t…
Learning to solve sequential tasks with recurrent models requires the ability to memorize long sequences and to extract task-relevant features from them. In this paper, we study the memorization subtask from the point of view of the design and training of recurrent neural networks. We propose a new model, the Linear Me…
Recurrent neural networks can learn complex transduction problems that require maintaining and actively exploiting a memory of their inputs. Such models traditionally consider memory and input-output functionalities indissolubly entangled. We introduce a novel recurrent architecture based on the conceptual separation b…
In this paper we will try to assess the multifractality displayed by the high-frequency returns of Madrid's Stock Exchange IBEX35 index. A Multifractal Detrended Fluctuation Analysis shows that this index has a wide singularity spectrum which is most likely caused by its long memory. Our findings also show that this lo…
A new model decomposes equity returns and volatilities into memory components.
New matrix approximation method using RBF components for better memory efficiency.
mGRN improves multivariate time series prediction by managing marginal and joint memories.
Multivariate time series forecasting is extensively studied throughout the years with ubiquitous applications in areas such as finance, traffic, environment, etc. Still, concerns have been raised on traditional methods for incapable of modeling complex patterns or dependencies lying in real word data. To address such c…
Muon outperforms GD in associative memory learning by balancing frequency components.
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
Unified model explains volatility memory in stocks and forex.
We consider a financial market model driven by an R^n-valued Gaussian process with stationary increments which is different from Brownian motion. This driving noise process consists of independent components, and each component has memory described by two parameters. For this market model, we explicitly solve optim…
The paper introduces a new short rate model with memory components.
New memory allocation scheme improves image generation performance.
Memory networks are neural networks with an explicit memory component that can be both read and written to by the network. The memory is often addressed in a soft way using a softmax function, making end-to-end training with backpropagation possible. However, this is not computationally scalable for applications which …
We introduce a lifelong language learning setup where a model needs to learn from a stream of text examples without any dataset identifier. We propose an episodic memory model that performs sparse experience replay and local adaptation to mitigate catastrophic forgetting in this setup. Experiments on text classificatio…
Max-norm regularizer has been extensively studied in the last decade as it promotes an effective low-rank estimation for the underlying data. However, such max-norm regularized problems are typically formulated and solved in a batch manner, which prevents it from processing big data due to possible memory budget. In th…
In this paper we propose a new algorithm for streaming principal component analysis. With limited memory, small devices cannot store all the samples in the high-dimensional regime. Streaming principal component analysis aims to find the -dimensional subspace which can explain the most variation of the -dimensiona…
This paper presents a novel framework for predicting shot location and type in tennis. Inspired by recent neuroscience discoveries we incorporate neural memory modules to model the episodic and semantic memory components of a tennis player. We propose a Semi Supervised Generative Adversarial Network architecture that c…
LSTMs and GRUs are the most common recurrent neural network architectures used to solve temporal sequence problems. The two architectures have differing data flows dealing with a common component called the cell state (also referred to as the memory). We attempt to enhance the memory by presenting a modification that w…
New fair PCA method using streaming algorithms with statistical guarantees.
Global Memory Augmentation (GMAT) improves Transformer performance on long documents.
We present a federated, asynchronous, and -differentially private algorithm for PCA in the memory-limited setting. Our algorithm incrementally computes local model updates using a streaming procedure and adaptively estimates its leading principal components when only memory is av…
This study examines memory effects in S&P500 market correlations using Langevin models.
Language Models (LMs) are important components in several Natural Language Processing systems. Recurrent Neural Network LMs composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results. However, these models still struggle to process long sequences which are more li…
Study of coupled Hawkes processes with rough-volatility limits.
SGQuant reduces GNN memory usage without significant accuracy loss.
A novel memory mechanism for reinforcement learning agents that stores past events in human-readable language.
In the current context of data explosion, online techniques that do not require storing all data in memory are indispensable to routinely perform tasks like principal component analysis (PCA). Recursive algorithms that update the PCA with each new observation have been studied in various fields of research and found wi…
The study uses Markov chains to forecast cryptocurrency market dynamics.
Proposes a CL technique to improve accuracy and reduce forgetting.
New method combines long-memory reservoirs for accurate dengue forecasting from short data.
A method models nonlinear dynamics from data using barycentric coordinates and memory.
We consider streaming, one-pass principal component analysis (PCA), in the high-dimensional regime, with limited memory. Here, -dimensional samples are presented sequentially, and the goal is to produce the -dimensional subspace that best approximates these points. Standard algorithms require memory; mea…
LSTM-MDNs improve risk forecasting during turbulent periods.
PySAD offers a unified Python framework for efficient streaming anomaly detection.
Principal components analysis (PCA) is a fundamental algorithm in data analysis. Its memory-restricted online versions are useful in many modern applications, where the data are too large to fit in memory, or when data arrive as a stream of items. In this paper, we propose ROIPCA and fROIPCA, two online PCA algorithms …
Essential principal components simplify spectral analysis with minimal training data.
New magnetic memory effects found in gravitational waves and memory.
We investigate the two components of the total daily return (close-to-close), the overnight return (close-to-open) and the daytime return (open-to-close), as well as the corresponding volatilities of the 2215 NYSE stocks from 1988 to 2007. The tail distribution of the volatility, the long-term memory in the sequence, a…
Robust PCA methods are typically batch algorithms which requires loading all observations into memory before processing. This makes them inefficient to process big data. In this paper, we develop an efficient online robust principal component methods, namely online moving window robust principal component analysis (OMW…
A new model learns preferences incrementally without personal data.
The computation of the sparse principal component of a matrix is equivalent to the identification of its principal submatrix with the largest maximum eigenvalue. Finding this optimal submatrix is what renders the problem -hard. In this work, we prove that, if the matrix is positive semidefinite and its …
Conversational agents such as Cortana, Alexa and Siri are continuously working on increasing their capabilities by adding new domains. The support of a new domain includes the design and development of a number of NLU components for domain classification, intents classification and slots tagging (including named entity…
Prototype-based memory network learns visual categories from unlabeled data.
We introduce a simple analysis of the structural complexity of infinite-memory processes built from random samples of stationary, ergodic finite-memory component processes. Such processes are familiar from the well known multi-arm Bandit problem. We contrast our analysis with computation-theoretic and statistical infer…