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.
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 …
Enhanced LSTM model learns complex temporal dependencies.
Memory-limited learning tackles adversarial bandits with reduced storage.
Paper proposes a GPU-based system for training massive deep learning models in ads systems.
Learning and memory are intertwined in our brain and their relationship is at the core of several recent neural network models. In particular, the Attention-Gated MEmory Tagging model (AuGMEnT) is a reinforcement learning network with an emphasis on biological plausibility of memory dynamics and learning. We find that …
New method reduces memory usage in deep HRNNs by replacing gradient backpropagation with local losses.
This paper introduces a hierarchical associative memory model with multiple layers.
We present memory-efficient and scalable algorithms for kernel methods used in machine learning. Using hierarchical matrix approximations for the kernel matrix the memory requirements, the number of floating point operations, and the execution time are drastically reduced compared to standard dense linear algebra routi…
This paper proposes a new approach to Transformers by integrating hierarchical associative memory with MetaFormers.
HTMRL uses HTM for RL, adapting faster to changing environments.
Efficiently discovers Bayesian network structure with reduced memory usage.
We present an end-to-end trained memory system that quickly adapts to new data and generates samples like them. Inspired by Kanerva's sparse distributed memory, it has a robust distributed reading and writing mechanism. The memory is analytically tractable, which enables optimal on-line compression via a Bayesian updat…
V-HMN integrates memory mechanisms for improved image recognition.
Enhanced financial trading system using multi-agent LLMs with layered memory.
Data aggregation improves HAC for resource-constrained systems.
Improved text summarization using neural semantic encoders with hierarchical structure.
Efficient memory layer improves graph neural networks for graph classification and regression.
Product Kanerva Machines dynamically combine smaller models for better memory organization.
The extension of deep learning towards temporal data processing is gaining an increasing research interest. In this paper we investigate the properties of state dynamics developed in successive levels of deep recurrent neural networks (RNNs) in terms of short-term memory abilities. Our results reveal interesting insigh…
A novel extrapolation method is proposed for longitudinal forecasting. A hierarchical Gaussian process model is used to combine nonlinear population change and individual memory of the past to make prediction. The prediction error is minimized through the hierarchical design. The method is further extended to joint mod…
We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support Vector Machine (SVM) in order to reduce the amount of computations, based on the pr…
New memory allocation scheme improves image generation performance.
Hierarchical temporal memory (HTM) is an emerging machine learning algorithm, with the potential to provide a means to perform predictions on spatiotemporal data. The algorithm, inspired by the neocortex, currently does not have a comprehensive mathematical framework. This work brings together all aspects of the spatia…
A new algorithm speeds up convex clustering.
BoRA finetunes multi-task LLMs by sharing information through hierarchical priors.
Paper shows intrinsic motivation boosts exploration efficiency in HRL.
STanHop predicts multivariate time series with memory-enhanced capabilities.
NEST optimizes deep learning training by placing devices efficiently across networks and memory.
HMN detects fake faces using memory networks and visual cues.
Large-scale Hierarchical Classification (HC) involves datasets consisting of thousands of classes and millions of training instances with high-dimensional features posing several big data challenges. Feature selection that aims to select the subset of discriminant features is an effective strategy to deal with large-sc…
We propose a practical and scalable Gaussian process model for large-scale nonlinear probabilistic regression. Our mixture-of-experts model is conceptually simple and hierarchically recombines computations for an overall approximation of a full Gaussian process. Closed-form and distributed computations allow for effici…
Both the human brain and artificial learning agents operating in real-world or comparably complex environments are faced with the challenge of online model selection. In principle this challenge can be overcome: hierarchical Bayesian inference provides a principled method for model selection and it converges on the sam…
We propose that the Continual Learning desiderata can be achieved through a neuro-inspired architecture, grounded on Mountcastle's cortical column hypothesis. The proposed architecture involves a single module, called Self-Taught Associative Memory (STAM), which models the function of a cortical column. STAMs are repea…
CoHiRF extends clustering methods to handle high-dimensional data efficiently.
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…
Paper develops a framework for generating coherent image captions using visual features and hierarchical topics.
Deep generative models have achieved great success in unsupervised learning with the ability to capture complex nonlinear relationships between latent generating factors and observations. Among them, a factorized hierarchical variational autoencoder (FHVAE) is a variational inference-based model that formulates a hiera…
Two novel search strategies reduce complexity for target localization with size-dependent noise.
Sparse deep neural networks(DNNs) are efficient in both memory and compute when compared to dense DNNs. But due to irregularity in computation of sparse DNNs, their efficiencies are much lower than that of dense DNNs on regular parallel hardware such as TPU. This inefficiency leads to poor/no performance benefits for s…
Training deep recurrent neural network (RNN) architectures is complicated due to the increased network complexity. This disrupts the learning of higher order abstracts using deep RNN. In case of feed-forward networks training deep structures is simple and faster while learning long-term temporal information is not poss…
Local-HDP learns independent topics for each 3D object category in real-time.
This paper tackles multilingual speech processing by optimizing conflicting objectives hierarchically.
Recent advances in representation learning on graphs, mainly leveraging graph convolutional networks, have brought a substantial improvement on many graph-based benchmark tasks. While novel approaches to learning node embeddings are highly suitable for node classification and link prediction, their application to graph…
We propose a novel class of kernels to alleviate the high computational cost of large-scale nonparametric learning with kernel methods. The proposed kernel is defined based on a hierarchical partitioning of the underlying data domain, where the Nyström method (a globally low-rank approximation) is married with a locall…
Improved neural network approximations for statistical systems.
Muon outperforms GD in associative memory learning by balancing frequency components.
FinMem enhances LLM trading agents with layered memory and character design.
Novel algorithm speeds up log-determinant estimation for large matrices.