arXiv research

A new approach to group fairness treats it as a bargaining problem.

We give several Bishop-Gromov relative volume comparisons with integral Ricci curvature which improve the results in \cite{PW1}. Using one of these volume comparisons, we derive an estimate for the volume entropy in terms of integral Ricci curvature which substantially improves an earlier estimate in \cite{Au2} and giv…

Inference for normal and Monte Carlo distributions using minimum relative entropy.

RGRR allocates between QQQ and DIA based on relative states, improving Sharpe and CAGR.

In this paper, improving a preceding work, we obtain asymptotic polybalanced kernels associated to extremal Kaehler metrics on polarized algebraic manifolds. As a corollary, we have a stronger asymptotic relative Chow-polystability for extremal Kaehler polarized algebraic manifolds. Finally, related to the Yau-Tian-Don…

CV inference can be invalid for relatively unstable model comparisons.

Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce spectral variation in the input signal. This has also been confirmed experimentally, with CNNs showing improvements in word error rate (WER) between 4-12% relative compared to DNNs across a var…

Improved text-to-image and multimodal understanding through adaptive generation order optimization.

Improved robustness in ASR systems with speaker adaptation.

Logistic regression is a widely used method in several fields. When applying logistic regression to imbalanced data, for which majority classes dominate over minority classes, all class labels are estimated as `majority class.' In this article, we use an F-measure optimization method to improve the performance of logis…

The study assesses the relative value of prediction in algorithmic decision making.

Study improves sampling from non-log-concave distributions using Fisher information.

Adapts GRPO for off-policy RL, improving reward.

Paper proposes a federated learning framework for relative fairness.

Adaptive compute allocation improves model performance by prioritizing harder queries.

Meta-learning improves relative density-ratio estimation from limited data.

Introduces relative information gain for improving Gaussian process regression rates.

OGRePy simplifies tensor calculations in general relativity.

The CUR matrix decomposition is an important extension of Nyström approximation to a general matrix. It approximates any data matrix in terms of a small number of its columns and rows. In this paper we propose a novel randomized CUR algorithm with an expected relative-error bound. The proposed algorithm has the advanta…

Ensembling improves performance when classifiers disagree more than average.

A machine learning model improves relative valuation of municipal bonds.

OGRe simplifies tensor calculations in general relativity.

We generalize the Weinstein-Moser theorem on the existence of nonlinear normal modes (i.e., periodic orbits) near an equilibrium in a Hamiltonian system to a theorem on the existence of relative periodic orbits near a relative equilibrium in a Hamiltonian system with continuous symmetries. More specifically we signific…

In 2018, at the World Economic Forum in Davos it was presented a new countries' economic performance metric named the Inclusive Development Index (IDI) composed of 12 indicators. The new metric implies that countries might need to realize structural reforms for improving both economic expansion and social inclusion per…

Regularization is important for end-to-end speech models, since the models are highly flexible and easy to overfit. Data augmentation and dropout has been important for improving end-to-end models in other domains. However, they are relatively under explored for end-to-end speech models. Therefore, we investigate the e…

Sophisticated volatility models outperform naive portfolio strategies.

We propose an extension of the concept of Expected Improvement criterion commonly used in Kriging based optimization. We extend it for more complex Kriging models, e.g. models using derivatives. The target field of application are CFD problems, where objective function are extremely expensive to evaluate, but the theor…

REMEDI improves neural entropy estimation across various tasks.

Improved neural speaker embeddings enhance ASR performance.

The paper provides tight bounds for improving multi-armed bandits problem.

AV-ASR system improves speech recognition with visual context.

Study on local elasticity in neural network training, improving detection of class-specific changes.

Improved code translation by preserving structure with composed fine-tuning.

New method improves optimization algorithms without Lipschitz smoothness.

We refine a metric bunching estimate for pinched manifolds.

This paper addresses the robust speech recognition problem as an adaptation task. Specifically, we investigate the cumulative application of adaptation methods. A bidirectional Long Short-Term Memory (BLSTM) based neural network, capable of learning temporal relationships and translation invariant representations, is u…

We advance the state of the art in polyphonic piano music transcription by using a deep convolutional and recurrent neural network which is trained to jointly predict onsets and frames. Our model predicts pitch onset events and then uses those predictions to condition framewise pitch predictions. During inference, we r…

Unified estimate for complex Monge-Ampère equations on Kähler manifolds.

New boundary conditions improve Hamiltonian analysis in GR.

AGMMNs improve learning of copula models by adaptively selecting kernels.

Piecewise Aggregate Approximation (PAA) is a competitive basic dimension reduction method for high-dimensional time series mining. When deployed, however, the limitations are obvious that some important information will be missed, especially the trend. In this paper, we propose two new approaches for time series that u…

Time series forecasting is one of the most active research topics. Machine learning methods have been increasingly adopted to solve these predictive tasks. However, in a recent work, these were shown to systematically present a lower predictive performance relative to simple statistical methods. In this work, we counte…

CoDistill-GRPO improves small models in GRPO by distilling knowledge from a larger model.

The paper introduces new inequalities for knots in 4D cobordisms.

Bayesian nonparametric models improve OOD detection, especially with complex covariance structures.

Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task. While this problem has been well investigated, the related problem of {\em online} IRL---where the observations are incrementally accrued, yet the demands of the application often…

New methods estimate survival functions with time-varying covariates.

The study extends SPT to account for real-world transaction costs, improving portfolio performance.