arXiv research

Stochastic Gradient Descent shows directional bias with moderate learning rates, impacting optimization outcomes.

Optimal learning via moderate deviations theory improves statistical accuracy.

We provide a unifying treatment of pathwise moderate deviations for models commonly used in financial applications, and for related integrated functionals. Suitable scaling allows us to transfer these results into small-time, large-time and tail asymptotics for diffusions, as well as for option prices and realised vari…

New lower bounds show challenges in clustering in moderate dimensions.

Proposes a method for interpreting time-varying causal effect moderation in high-dimensional data.

SGD with large learning rates can achieve better test accuracy than expected.

New method interprets deep learning for causal effects, separating prognostic and moderating covariates.

Large learning rates prevent memorization in denoising score matching.

Bayesian neural networks explore rare fluctuations for better feature learning.

The study shows interest rates impact investment and funding negatively but positively on dividend decisions.

Study describes frequencies of geodesics on hyperbolic surfaces as genus grows.

For spherically symmetric distributions, efficient quantisation can be achieved with moderate sample sizes.

Paper optimizes change-point detection using learned distributions from training sequences.

Enhances content moderation with culturally-aware models.

Risk estimation is at the core of many learning systems. The importance of this problem has motivated researchers to propose different schemes, such as cross validation, generalized cross validation, and Bootstrap. The theoretical properties of such estimates have been extensively studied in the low-dimensional setting…

Optimizes variance reduction in Heston model using large and moderate deviations.

This paper addresses the problem of blind demixing of instantaneous mixtures in a multiple-input multiple-output communication system. The main objective is to present efficient blind source separation (BSS) algorithms dedicated to moderate or high-order QAM constellations. Four new iterative batch BSS algorithms are p…

Importance sampling has become an important tool for the computation of tail-based risk measures. Since such quantities are often determined mainly by rare events standard Monte Carlo can be inefficient and importance sampling provides a way to speed up computations. This paper considers moderate deviations for the wei…

Cascade classifiers are widely used in real-time object detection. Different from conventional classifiers that are designed for a low overall classification error rate, a classifier in each node of the cascade is required to achieve an extremely high detection rate and moderate false positive rate. Although there are …

The paper tackles robust policy learning from multiple data sources.

Study measures investment funds' climate transition risk, finds moderate losses.

Q-learning with cSMART data assesses cAI tailoring variables.

We present an extended version of the recently proposed "LLOB" model for the dynamics of latent liquidity in financial markets. By allowing for finite cancellation and deposition rates within a continuous reaction-diffusion setup, we account for finite memory effects on the dynamics of the latent order book. We compute…

AUC is unreliable in rare event settings but stable with moderate numbers of events.

RQMC improves kernel-based learning by reducing deterministic error and offering computational advantages.

We extend previous large deviations results for the randomised Heston model to the case of moderate deviations. The proofs involve the Gärtner-Ellis theorem and sharp large deviations tools.

Computes invariants distinguishing between immersions and embeddings of doodles and blobs on surfaces.

Developers of text-to-speech synthesizers (TTS) often make use of human raters to assess the quality of synthesized speech. We demonstrate that we can model human raters' mean opinion scores (MOS) of synthesized speech using a deep recurrent neural network whose inputs consist solely of a raw waveform. Our best models …

Deep neural networks (DNNs) although achieving human-level performance in many domains, have very large model size that hinders their broader applications on edge computing devices. Extensive research work have been conducted on DNN model compression or pruning. However, most of the previous work took heuristic approac…

Unified approach to stochastic Volterra systems' deviations.

Modeling house prices in Australia reveals supply limitations as the primary driver of extreme trends.

We consider call option prices in diffusion models close to expiry, in an asymptotic regime ("moderately out of the money") that interpolates between the well-studied cases of at-the-money options and out-of-the-money fixed-strike options. First and higher order small-time moderate deviation estimates of call prices an…

A new graph-based clustering method for moderate-dimensional data.

Proposes a two-stage method for testing variable interactions with FDR control.

Post hoc test for Sharpe ratio improves pairwise comparisons.

Careful tuning of the learning rate, or even schedules thereof, can be crucial to effective neural net training. There has been much recent interest in gradient-based meta-optimization, where one tunes hyperparameters, or even learns an optimizer, in order to minimize the expected loss when the training procedure is un…

Gradient descent learns ReLU functions with non-zero bias efficiently.

SRRM improves recursive transport surrogates in the small-discrepancy regime.

The aim of this paper is to introduce a synthetic ALM model that catches the main specificity of life insurance contracts. First, it keeps track of both market and book values to apply the regulatory profit sharing rule. Second, it introduces a determination of the crediting rate to policyholders that is close to the p…

A novel k-NN method estimates conditional mean and variance efficiently.

We propose computationally efficient encoders and decoders for lossy compression using a Sparse Regression Code. The codebook is defined by a design matrix and codewords are structured linear combinations of columns of this matrix. The proposed encoding algorithm sequentially chooses columns of the design matrix to suc…

Machine learning models detect COVID-19 from routine blood tests.

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the capacity to fit any set of labels including random noise. However, given the hi…

The Basel II internal ratings-based (IRB) approach to capital adequacy for credit risk implements an asymptotic single risk factor (ASRF) model. Measurements from the ASRF model of the prevailing state of Australia's economy and the level of capitalisation of its banking sector find general agreement with macroeconomic…

In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\geq 1$, i.e. functionals of the training data with low variance that take the form of averages over $k$-tuples. From a computational perspective, …

Paper generalizes VB-FTRL for online learning of quantum states with logarithmic loss.

This study optimizes DRL for American option hedging with new training methods.

Improves accuracy and fairness in prediction systems with multiple domain experts.