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-based models can learn to approximate Bayes-optimal predictors for non-stationary data.
In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual foundations of this tool for building new, scalable agents that operate on broad domains.…
Current deep neural networks can achieve remarkable performance on a single task. However, when the deep neural network is continually trained on a sequence of tasks, it seems to gradually forget the previous learned knowledge. This phenomenon is referred to as \textit{catastrophic forgetting} and motivates the field c…
Deep neural networks have excelled on a wide range of problems, from vision to language and game playing. Neural networks very gradually incorporate information into weights as they process data, requiring very low learning rates. If the training distribution shifts, the network is slow to adapt, and when it does adapt…
Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph. We also introduce two new networks based on this layer: memory-based GNN (MemGNN)…
Many robotic applications require the agent to perform long-horizon tasks in partially observable environments. In such applications, decision making at any step can depend on observations received far in the past. Hence, being able to properly memorize and utilize the long-term history is crucial. In this work, we pro…
A method to improve sequential learning by keeping past data errors in check.
A new memory-based fusion layer improves multi-modal deep learning performance.
Reinforcement learning (RL) algorithms have made huge progress in recent years by leveraging the power of deep neural networks (DNN). Despite the success, deep RL algorithms are known to be sample inefficient, often requiring many rounds of interaction with the environments to obtain satisfactory performance. Recently,…
MTRGL learns temporal correlations from multi-modal data for improved pair trading.
The study shows how modular learning can adapt to new tasks.
GMED edits stored examples to improve continual learning.
New framework learns policies for partially observable systems.
Recommender systems are personalized: we expect the results given to a particular user to reflect that user's preferences. Some researchers have studied the notion of calibration, how well recommendations match users' stated preferences, and bias disparity the extent to which mis-calibration affects different user grou…
Distributed stochastic gradient descent~(DSGD) has been widely used for optimizing large-scale machine learning models, including both convex and non-convex models. With the rapid growth of model size, huge communication cost has been the bottleneck of traditional DSGD. Recently, many communication compression methods …
We propose a primitive called PJOIN, for "predictive join," which combines and extends the operations JOIN and LINK, which Valiant proposed as the basis of a computational theory of cortex. We show that PJOIN can be implemented in Valiant's model. We also show that, using PJOIN, certain reasonably complex learning and …
Real-time fuel leakage detection framework MOCPD improves accuracy.
NIPA aims to translate brain learning mechanisms into scalable Bayesian inference.
With the arrival of the big data era, more and more data are becoming readily available in various real-world applications and those data are usually highly heterogeneous. Taking computational medicine as an example, we have both Electronic Health Records (EHR) and medical images for each patient. For complicated disea…
Given a system of equations in a "random" finitely generated subgroup of the braid group, we show how to find a small ordered list of elements in the subgroup, which contains a solution to the equations with a significant probability. Moreover, with a significant probability, the solution will be the first in the list.…
This study combines two different learning paradigms, k-nearest neighbor (k-NN) rule, as memory-based learning paradigm and relevance vector machines (RVM), as statistical learning paradigm. This combination is performed in kernel space and is called k-relevance vector (k-RV). The purpose is to improve the performance …
The Industrial Internet of Things drastically increases connectivity of devices in industrial applications. In addition to the benefits in efficiency, scalability and ease of use, this creates novel attack surfaces. Historically, industrial networks and protocols do not contain means of security, such as authentication…
Meta learning with information theory and Gaussian processes.
New method prevents deep learning forgetting past by remembering key examples.
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…
Memory-based neural networks model temporal data by leveraging an ability to remember information for long periods. It is unclear, however, whether they also have an ability to perform complex relational reasoning with the information they remember. Here, we first confirm our intuitions that standard memory architectur…
Self-referential meta learning avoids explicit optimization by modifying itself.
Hybrid framework prevents forgetting in continual learning.
Mild Traumatic Brain Injury (mTBI) is a significant public health problem. The most troubling symptoms after mTBI are cognitive complaints. Studies show measurable differences between patients with mTBI and healthy controls with respect to tissue microstructure using diffusion MRI. However, it remains unclear which dif…
Long Short-Term Memory (LSTM) is a recurrent neural network (RNN) architecture that has been designed to address the vanishing and exploding gradient problems of conventional RNNs. Unlike feedforward neural networks, RNNs have cyclic connections making them powerful for modeling sequences. They have been successfully u…
Robotics has proved to be an indispensable tool in many industrial as well as social applications, such as warehouse automation, manufacturing, disaster robotics, etc. In most of these scenarios, damage to the agent while accomplishing mission-critical tasks can result in failure. To enable robotic adaptation in such s…
Paper analyzes convergence of continual learning with adaptive methods.
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…
Stable Hadamard Memory improves reinforcement learning by efficiently managing memory.
Many real-world tasks such as classification of digital histopathology images and 3D object detection involve learning from a set of instances. In these cases, only a group of instances or a set, collectively, contains meaningful information and therefore only the sets have labels, and not individual data instances. In…
Research benchmarks LLMs in medical domain to reduce hallucinations.
Paper introduces a new framework to improve sample efficiency in POMDPs learning.
This work proposes a novel neural network architecture, called the Dynamically Controlled Recurrent Neural Network (DCRNN), specifically designed to model dynamical systems that are governed by ordinary differential equations (ODEs). The current state vectors of these types of dynamical systems only depend on their sta…
Reinforcement learning with sparse rewards is challenging because an agent can rarely obtain non-zero rewards and hence, gradient-based optimization of parameterized policies can be incremental and slow. Recent work demonstrated that using a memory buffer of previous successful trajectories can result in more effective…
BeMF improves recommendation reliability in recommender systems.
Human categorization is one of the most important and successful targets of cognitive modeling in psychology, yet decades of development and assessment of competing models have been contingent on small sets of simple, artificial experimental stimuli. Here we extend this modeling paradigm to the domain of natural images…
Real time application of deep learning algorithms is often hindered by high computational complexity and frequent memory accesses. Network pruning is a promising technique to solve this problem. However, pruning usually results in irregular network connections that not only demand extra representation efforts but also …
We present a practical health-theme machine learning (ML) application concerning `AI for social good' domain for `Producing Good Outcomes' track. In particular, the solution is concerning the problem of a potential elderly adult dementia onset prediction in aging societies. The paper discusses our attempt and encouragi…
Study investigates how simple speech sounds can form abstract categories.
We propose a reinforcement learning agent to solve hard exploration games by learning a range of directed exploratory policies. We construct an episodic memory-based intrinsic reward using k-nearest neighbors over the agent's recent experience to train the directed exploratory policies, thereby encouraging the agent to…
Time series forecasting is ubiquitous in the modern world. Applications range from health care to astronomy, and include climate modelling, financial trading and monitoring of critical engineering equipment. To offer value over this range of activities, models must not only provide accurate forecasts, but also quantify…
Logarithmic-time schedules boost large-scale language model training efficiency.
Attention improves edge prediction in e-commerce graphs.