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.
VSML unifies meta learning concepts and enables simple backpropagation.
Meta-ticket finds optimal sparse subnetworks for few-shot learning in randomly initialized neural networks.
NNs can learn efficient algorithms for certain problems.
New attention mechanism improves meta-transfer learning in dynamic tasks.
Meta-learning algorithms prepare quantum Gibbs states efficiently for NISQ devices.
Much combinatorial optimisation problems constitute a non-polynomial (NP) hard optimisation problem, i.e., they can not be solved in polynomial time. One such problem is finding the shortest route between two nodes on a graph. Meta-heuristic algorithms such as along with mixed-integer programming (MIP) methods …
Bayesian meta-reinforcement learning improves over point estimates with Laplace approximation.
Dida learns meta-features invariant to feature permutations.
A current research trend in neurocomputing involves the design of novel artificial neural networks incorporating the concept of time into their operating model. In this paper, a novel architecture that employs stigmergy is proposed. Computational stigmergy is used to dynamically increase (or decrease) the strength of a…
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…
Proposes a Siamese NN for algorithm selection focusing on alike performing instances.
POLA adapts learning rates for online time series prediction.
We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established usin…
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to…
Proposes a new CG interpretation of neural networks for better theoretical analysis.
Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-…
In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applications is their demand for massive amounts of training data. A critical present objective is thus to develop deep RL methods that can adapt rap…
Meta-learning improves event prediction from short sequences.
Meta-GLAR combines global deep representations with local adaptation for improved forecasting accuracy.
A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph. Often meta-heuristics algorithms such as are employed on graphs with a large number of nodes. Here, we propose a deep recurrent neural network architecture based on the Sequence-2-Seque…
Novel algorithms improve efficiency of finite width NTK computation.
SYNTHONY selects tabular synthesizers based on stress profiling and user intent.
CHAMELEON uses RNNs to recommend news sequences better than other methods.
Machine Learning (ML) applications on healthcare can have a great impact on people's lives helping deliver better and timely treatment to those in need. At the same time, medical data is usually big and sparse requiring important computational resources. Although it might not be a problem for wide-adoption of ML tools …
Model predicts COVID-19 spread with better accuracy than existing methods.
Paper tackles uncertainty prediction for deep sequential regression.
Stochastic gradient Markov chain Monte Carlo (SG-MCMC) has become increasingly popular for simulating posterior samples in large-scale Bayesian modeling. However, existing SG-MCMC schemes are not tailored to any specific probabilistic model, even a simple modification of the underlying dynamical system requires signifi…
How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just li…
Typical reinforcement learning (RL) agents learn to complete tasks specified by reward functions tailored to their domain. As such, the policies they learn do not generalize even to similar domains. To address this issue, we develop a framework through which a deep RL agent learns to generalize policies from smaller, s…
Unified GARCH-NN models improve financial volatility forecasting.
Likelihood-free inference is concerned with the estimation of the parameters of a non-differentiable stochastic simulator that best reproduce real observations. In the absence of a likelihood function, most of the existing inference methods optimize the simulator parameters through a handcrafted iterative procedure tha…
Discovering and exploiting the causal structure in the environment is a crucial challenge for intelligent agents. Here we explore whether causal reasoning can emerge via meta-reinforcement learning. We train a recurrent network with model-free reinforcement learning to solve a range of problems that each contain causal…
The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora. Past distances between documents suffer from either an inability to incorporate semantic similarities between words or from scalability issues. As an alternative, we introduce hierarchical optimal transp…
Recently, neural networks trained as optimizers under the "learning to learn" or meta-learning framework have been shown to be effective for a broad range of optimization tasks including derivative-free black-box function optimization. Recurrent neural networks (RNNs) trained to optimize a diverse set of synthetic non-…
We propose a simple approach which, given distributed computing resources, can nearly achieve the accuracy of -NN prediction, while matching (or improving) the faster prediction time of -NN. The approach consists of aggregating denoised -NN predictors over a small number of distributed subsamples. We show, bot…
Recurrent neural networks (RNNs) for reinforcement learning (RL) have shown distinct advantages, e.g., solving memory-dependent tasks and meta-learning. However, little effort has been spent on improving RNN architectures and on understanding the underlying neural mechanisms for performance gain. In this paper, we prop…
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models that have been trained on the samples from specific tasks, thus leaving the task…
A new stochastic method tackles bi-level optimization problems in deep learning.
A new method for name disambiguation in academic networks using multi-view attention and recurrent neural networks.
In this paper, a novel architecture of Recurrent Neural Network (RNN) is designed and experimented. The proposed RNN adopts a computational memory based on the concept of stigmergy. The basic principle of a Stigmergic Memory (SM) is that the activity of deposit/removal of a quantity in the SM stimulates the next activi…
Meta-learning model clusters data better than standard methods.
Randomly trained neural networks can generalize well if there's a simpler underlying teacher model.
This paper analyzes deep Stable neural networks, showing convergence rates under different growth settings.
Study bridges GARCH and NN models for volatility forecasting.
A primary goal of computational phenotype research is to conduct medical diagnosis. In hospital, physicians rely on massive clinical data to make diagnosis decisions, among which laboratory tests are one of the most important resources. However, the longitudinal and incomplete nature of laboratory test data casts a sig…
Paper proposes MS-k-NN for improved convergence rate in k-NN classification.
A fast method for LOOCV in k-NN regression reduces computation time.
Adds layers to NNs to protect them from reverse engineering.