arXiv research

mGRN improves multivariate time series prediction by managing marginal and joint memories.

Study shows how to balance memory and learning efficiency in continual learning.

Agents learn and control complex mechanical systems through shared memories.

The properties of statistical tests for hypotheses concerning the parameters of the multifractal model of asset returns (MMAR) are investigated, using Monte Carlo techniques. We show that, in the presence of multifractality, conventional tests of long memory tend to over-reject the null hypothesis of no long memory. Ou…

Bayesian LSTM model improves VaR and ES forecasting accuracy.

Estimating multiple sparse Gaussian Graphical Models (sGGMs) jointly for many related tasks (large $K$) under a high-dimensional (large $p$) situation is an important task. Most previous studies for the joint estimation of multiple sGGMs rely on penalized log-likelihood estimators that involve expensive and difficult n…

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…

Efficiently combines autoregressive and set-based models for joint distributions.

Efficiently preserves old class knowledge in memory-limited settings.

Joslim optimizes both width and weight configurations for slimmable neural networks, improving model efficiency.

The paper examines how long-memory dynamics, rough-volatility, and persistence affect equity volatility forecasting.

Intelligence emerges from stabilizing invariant cycles in memory.

Status prediction and anomaly detection are two fundamental tasks in automatic IT systems monitoring. In this paper, a joint model Predictor & Anomaly Detector (PAD) is proposed to address these two issues under one framework. In our design, the variational auto-encoder (VAE) and long short-term memory (LSTM) are joine…

Novel bounds for deep MDA algorithms improve performance and efficiency.

New GP-VAE model improves scalability and performance.

The paper analyzes the joint dynamics of prices and order flow in electronic order books.

Recurrent neural networks like long short-term memory (LSTM) are important architectures for sequential prediction tasks. LSTMs (and RNNs in general) model sequences along the forward time direction. Bidirectional LSTMs (Bi-LSTMs) on the other hand model sequences along both forward and backward directions and are gene…

Long Short-Term Memory (LSTM) is one of the most powerful sequence models. Despite the strong performance, however, it lacks the nice interpretability as in state space models. In this paper, we present a way to combine the best of both worlds by introducing State Space LSTM (SSL) models that generalizes the earlier wo…

Ensembles of models have been empirically shown to improve predictive performance and to yield robust measures of uncertainty. However, they are expensive in computation and memory. Therefore, recent research has focused on distilling ensembles into a single compact model, reducing the computational and memory burden o…

Study integrates attentional and spacing factors to improve category learning models.

SRMC framework reduces Monte Carlo variance by history-based sampling in high-dimensional spaces.

H-GAT improves stock selection by capturing complex higher-order stock relations and integrating both technical and fundamental analysis.

Bilinear models such as DistMult and ComplEx are effective methods for knowledge graph (KG) completion. However, they require large batch sizes, which becomes a performance bottleneck when training on large scale datasets due to memory constraints. In this paper we use occurrences of entity-relation pairs in the datase…

Extends geostatistical simulation method to handle multiple variables and large grids.

We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two separate latent spaces, for sentences and syntactic trees. The evidence lower bound…

Proposes a novel SAM operator for separate item and relational memories.

In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory …

TERA method speeds up derivative Gaussian processes in high dimensions.

Flow-based generative models parameterize probability distributions through an invertible transformation and can be trained by maximum likelihood. Invertible residual networks provide a flexible family of transformations where only Lipschitz conditions rather than strict architectural constraints are needed for enforci…

An unsupervised anomaly detection method for irregularly sampled time-series data.

Stable Hadamard Memory improves reinforcement learning by efficiently managing memory.

The paper explores the relationship between joint mixability and negative dependence structures.

We introduce a general tensor model suitable for data analytic tasks for {\em heterogeneous} datasets, wherein there are joint low-rank structures within groups of observations, but also discriminative structures across different groups. To capture such complex structures, a double core tensor (DCOT) factorization mode…

New memory allocation scheme improves image generation performance.

DAM with MRL improves relational reasoning in MANNs.

AbDiffuser generates full-atom antibodies with sequence and structure fidelity.

We discuss memory models which are based on tensor decompositions using latent representations of entities and events. We show how episodic memory and semantic memory can be realized and discuss how new memory traces can be generated from sensory input: Existing memories are the basis for perception and new memories ar…

Model combines long-term and short-term memory using conceptors.

We discuss the general properties of the theory of joint invariants of a smooth Lie group action in a manifold. Many of the known results about differential invariants, including Lie's finiteness theorem, have simpler versions in the context of joint invariants. We explore the relation between joint and differential in…

FJS method improves multinomial classification accuracy.

We provide a theoretical foundation for non-parametric estimation of functions of random variables using kernel mean embeddings. We show that for any continuous function $f$, consistent estimators of the mean embedding of a random variable $X$ lead to consistent estimators of the mean embedding of $f(X)$. For Matérn ke…

Paper proposes a new method to evaluate joint risk under uncertainty.

Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorte…

Introduces joint Shapley values to measure feature importance in models.

We consider the fully decentralized machine learning scenario where many users with personal datasets collaborate to learn models through local peer-to-peer exchanges, without a central coordinator. We propose to train personalized models that leverage a collaboration graph describing the relationships between user per…

Study proposes a new model for joint survival annuity valuation.

In recent years, memory-augmented neural networks(MANNs) have shown promising power to enhance the memory ability of neural networks for sequential processing tasks. However, previous MANNs suffer from complex memory addressing mechanism, making them relatively hard to train and causing computational overheads. Moreove…

Enhanced Hopfield model boosts memory retrieval capacity.