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.
Quantum machine learning offers advantages for broader learning tasks.
Two new criteria help understand the advantage of deep neural networks.
Quantum circuits reveal pathways to dequantization in machine learning models.
Modified BFGS and LBFGS++ libraries boost performance for non-parallelizable functions.
New algorithm learns value and advantage functions for continuous-time Markov processes without structural assumptions.
We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function…
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…
Study compares adaptive vs fixed query learning methods.
Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep -learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the …
Deep neural networks outperform other methods in estimating non-smooth functions with singularities.
New approach optimizes policies in adversarial MDPs using adversarial learning.
New method learns time-varying home field advantage in football.
New algorithm achieves logarithmic regret for adversarial online control.
Gaussian processes (GPs) are nonparametric priors over functions. Fitting a GP implies computing a posterior distribution of functions consistent with the observed data. Similarly, deep Gaussian processes (DGPs) should allow us to compute a posterior distribution of compositions of multiple functions giving rise to the…
The most widely used activation functions in current deep feed-forward neural networks are rectified linear units (ReLU), and many alternatives have been successfully applied, as well. However, none of the alternatives have managed to consistently outperform the rest and there is no unified theory connecting properties…
Random Function Descent improves optimization in high dimensions.
One question central to Reinforcement Learning is how to learn a feature representation that supports algorithm scaling and re-use of learned information from different tasks. Successor Features approach this problem by learning a feature representation that satisfies a temporal constraint. We present an implementation…
Paper proposes efficient cost functions for automated market makers in DeFi.
Deep networks learn hierarchical functions more efficiently than shallow ones.
Decussation improves robustness of 3D neural networks.
The logcosh loss function helps neural networks learn set-valued functions better.
This paper introduces and develops a novel variable importance score function in the context of ensemble learning and demonstrates its appeal both theoretically and empirically. Our proposed score function is simple and more straightforward than its counterpart proposed in the context of random forest, and by avoiding …
MB-DQN uses different backup lengths for improved reinforcement learning.
Real-world tasks are often highly structured. Hierarchical reinforcement learning (HRL) has attracted research interest as an approach for leveraging the hierarchical structure of a given task in reinforcement learning (RL). However, identifying the hierarchical policy structure that enhances the performance of RL is n…
Woodbury transformations improve deep generative models with efficient invertibility and determinant calculation.
Sparse activations in neural networks are hard to exploit but lead to advantages in learning.
We developed OmicsMapNet approach to take advantage of existing deep leaning frameworks to analyze high-dimensional omics data as 2-dimensional images. The omics data of individual samples were first rearranged into 2D images in which molecular features related in functions, ontologies, or other relationships were orga…
Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.
The optimal policy of a reinforcement learning problem is often discontinuous and non-smooth. I.e., for two states with similar representations, their optimal policies can be significantly different. In this case, representing the entire policy with a function approximator (FA) with shared parameters for all states may…
Motivated by the problem of tuning hyperparameters in machine learning, we present a new approach for gradually and adaptively optimizing an unknown function using estimated gradients. We validate the empirical performance of the proposed idea on both low and high dimensional problems. The experimental results demonstr…
This survey is an introduction to positive definite kernels and the set of methods they have inspired in the machine learning literature, namely kernel methods. We first discuss some properties of positive definite kernels as well as reproducing kernel Hibert spaces, the natural extension of the set of functions $\{k(x…
We propose a simple method that combines neural networks and Gaussian processes. The proposed method can estimate the uncertainty of outputs and flexibly adjust target functions where training data exist, which are advantages of Gaussian processes. The proposed method can also achieve high generalization performance fo…
We study gradient bounds and other functional inequalities for the diffusion semigroup generated by Kolmogorov type operators. The focus is on two different methods: coupling techniques and generalized -calculus techniques. The advantages and drawbacks of each of these methods are discussed.
In the multiple linear regression setting, we propose a general framework, termed weighted orthogonal components regression (WOCR), which encompasses many known methods as special cases, including ridge regression and principal components regression. WOCR makes use of the monotonicity inherent in orthogonal components …
Infinite horizon off-policy policy evaluation is a highly challenging task due to the excessively large variance of typical importance sampling (IS) estimators. Recently, Liu et al. (2018a) proposed an approach that significantly reduces the variance of infinite-horizon off-policy evaluation by estimating the stationar…
After presenting Actor Critic Methods (ACM), we show ACM are control variate estimators. Using the projection theorem, we prove that the Q and Advantage Actor Critic (A2C) methods are optimal in the sense of the norm for the control variate estimators spanned by functions conditioned by the current state and acti…
This work is a further study on the Generalized Constraint Neural Network (GCNN) model [1], [2]. Two challenges are encountered in the study, that is, to embed any type of prior information and to select its imposing schemes. The work focuses on the second challenge and studies a new constraint imposing scheme for equa…
Quantum computers outperform classical methods in density modeling.
Quantum oracles help identify counterfactuals better than classical ones.
We consider a standard optimal investment problem in a complete financial market driven by a Wiener process and derive an explicit formula for the optimal portfolio process in terms of the vertical derivative from functional It^o calculus. An advantage with this approach compared to the Malliavin calculus approach is t…
This paper develops a slice sampler for Bayesian linear regression models with arbitrary priors. The new sampler has two advantages over current approaches. One, it is faster than many custom implementations that rely on auxiliary latent variables, if the number of regressors is large. Two, it can be used with any prio…
This paper improves Q-learning bounds using reference-advantage decomposition.
Quantum kernels offer potential speed-ups but require encoding problem-specific knowledge.
GP+ is a Python library for Gaussian process learning.
Proposes GPHMEs using Gaussian processes for hierarchical expert models.
The paper explores MAE as a loss function for DNN vector-to-vector regression, proving its advantages over MSE.
Conditional meta-learning improves meta-learning performance in diverse task environments.
We propose a MAP Bayesian approach to perform and evaluate a co-clustering of mixed-type data tables. The proposed model infers an optimal segmentation of all variables then performs a co-clustering by minimizing a Bayesian model selection cost function. One advantage of this approach is that it is user parameter-free.…