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.
Enhances graph neural networks by creating virtual data examples.
Parrot learns optimal cache replacement policies using imitation learning.
PSRL extension for continuing environments reduces regret.
Reinforcement learning usually uses the feedback rewards of environmental to train agents. But the rewards in the actual environment are sparse, and even some environments will not rewards. Most of the current methods are difficult to get good performance in sparse reward or non-reward environments. Although using shap…
New framework for PMD convergence in non-tabular environments.
The study explores how agents learn and adapt preferences in dynamic environments.
New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.
WMPG reduces policy gradient variance using world models.
New loss function equivalence reveals PER's uniform sampling can be improved.
An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory data is critical to the success of many beneficial applications such as health monitoring or activity recognition, a wide range of potentially …
We study algorithms for average-cost reinforcement learning problems with value function approximation. Our starting point is the recently proposed POLITEX algorithm, a version of policy iteration where the policy produced in each iteration is near-optimal in hindsight for the sum of all past value function estimates. …
Improves speech recognition in noisy environments using robust acoustic models.
Orthogonal frequency division multiplexing (OFDM) has been widely applied in current communication systems. The artificial intelligence (AI)-aided OFDM receivers are currently brought to the forefront to replace and improve the traditional OFDM receivers. In this study, we first compare two AI-aided OFDM receivers, nam…
Bayesian ATM improves stability and efficiency in mobile health interventions.
This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervis…
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace singl…
The fully connected layers of a deep convolutional neural network typically contain over 90% of the network parameters, and consume the majority of the memory required to store the network parameters. Reducing the number of parameters while preserving essentially the same predictive performance is critically important …
WiGS improves active learning for regression by dynamically selecting informative samples.
Spatial graphs study tangle replacement with equivalence classes.
We introduce new symplectic cut-and-paste operations that generalize the rational blowdown. In particular, we will define -replaceable plumbings to be those that, heuristically, can be symplectically replaced by Euler characteristic 4-manifolds. We will then classify 2-replaceable linear plumbings, construct 2-r…
Hybrid method improves SABR implied volatility approximation.
Physics-guided reinforcement learning optimizes swimming in turbulent flows.
Combining deep model-free reinforcement learning with on-line planning is a promising approach to building on the successes of deep RL. On-line planning with look-ahead trees has proven successful in environments where transition models are known a priori. However, in complex environments where transition models need t…
Efficiently samples sequences without replacement for machine learning models.
This paper addresses credit valuation adjustment with a new closeout convention.
In traditional reinforcement learning, an agent maximizes the reward collected during its interaction with the environment by approximating the optimal policy through the estimation of value functions. Typically, given a state s and action a, the corresponding value is the expected discounted sum of rewards. The optima…
Distributional reinforcement learning (DRL) is a recent reinforcement learning framework whose success has been supported by various empirical studies. It relies on the key idea of replacing the expected return with the return distribution, which captures the intrinsic randomness of the long term rewards. Most of the e…
SGD without replacement decouples into curvature-following and flatness-regularizing steps.
A new method prioritizes and recycles experiences for better reinforcement learning.
Approach to optimize bidding policies offline using reinforcement learning.
We consider the problem of fast time-series data clustering. Building on previous work modeling the correlation-based Hamiltonian of spin variables we present an updated fast non-expensive Agglomerative Likelihood Clustering algorithm (ALC). The method replaces the optimized genetic algorithm based approach (f-SPC) wit…
Develops algorithms to optimize machine replacement schedules using operational data.
New architecture separates object state and behavior for better game dynamics.
Tangle replacements help in understanding knot properties.
Convolutional neural networks have recently achieved significant breakthroughs in various image classification tasks. However, they are computationally expensive,which can make their feasible mplementation on embedded and low-power devices difficult. In this paper convolutional neural network binarization is implemente…
Smart contracts are a digital technology with potential but also flaws.
Traditional authentication systems use alphanumeric or graphical passwords, or token-based techniques that require "something you know and something you have". The disadvantages of these systems include the risks of forgetfulness, loss, and theft. To address these shortcomings, biometric authentication is rapidly repla…
We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample once. A naive application of auto-encoders in this setting encounters a major challenge: representa…
Paper closes convergence gap for SGD without replacement.
New method for simplifying knots with specific properties.
New k-means method handles random data better than traditional techniques.
If M and N are equivariantly homotopy equivalent G-manifolds, then the fixed sets M^G and N^G are also homotopy equivalent. The replacement problem asks the converse question: If F is homotopy equivalent to the fixed set M^G, is F = N^G for a G-manifold equivariantly homotopy equivalent to M? We prove that for locally …
Sampling without replacement speeds up optimization in minimax problems.
Thanks to the recent success of generative adversarial network (GAN) for image synthesis, there are many exciting GAN approaches that successfully synthesize MR image contrast from other images with different contrasts. These approaches are potentially important for image imputation problems, where complete set of data…
Being able to reach any desired location in the environment can be a valuable asset for an agent. Learning a policy to navigate between all pairs of states individually is often not feasible. An all-goals updating algorithm uses each transition to learn Q-values towards all goals simultaneously and off-policy. However …
New research disproves a key conjecture in optimization.
AdaDEM decouples EM into two parts to improve class overlap and uncertainty.
Two algorithms improve Federated RL in diverse environments.