arXiv research

Study examines how balancing methods affect model behavior in imbalanced classification problems.

MCNet improves uncertainty calibration in online advertising by modeling complex relations and balancing performance.

ADAPT method controls balance between sparse generator and discriminator in GANs.

Compared to in-clinic balance training, in-home training is not as effective. This is, in part, due to the lack of feedback from physical therapists (PTs). Here, we analyze the feasibility of using trunk sway data and machine learning (ML) techniques to automatically evaluate balance, providing accurate assessments out…

Estimates causal effects using neural networks for balancing covariates.

Balances the regret of different algorithms in bandit and RL problems.

TKIL improves class-balanced performance in incremental learning.

Neurons and networks in the cerebral cortex must operate reliably despite multiple sources of noise. To evaluate the impact of both input and output noise, we determine the robustness of single-neuron stimulus selective responses, as well as the robustness of attractor states of networks of neurons performing memory ta…

Balanced Activation improves object detection performance on long-tailed datasets.

The performance of classification algorithms with a massive and highly imbalanced data stream depends upon efficient balancing strategy. Some techniques of balancing strategy have been applied in the past with Batch data to resolve the class imbalance problem. This paper proposes a new incremental data balancing framew…

BI-MAML learns multiple tasks without forgetting old ones.

This study improves electricity price forecasting in the Irish balancing market.

A modified GAN improves thermal comfort classification models by balancing imbalanced datasets.

Water balance models (WBMs) are often employed to understand regional hydrologic cycles over various time scales. Most WBMs, however, are physically-based, and few employ state-of-the-art statistical methods to reconcile independent input measurement uncertainty and bias. Further, few WBMs exist for large lakes, and mo…

Paper proposes ARB-Loss to improve classification precision in imbalanced datasets.

CBDA improves active learning for semantic segmentation, especially with imbalanced classes.

New model reveals balance crucial for robust neural coding.

In this paper, we propose a deep reinforcement learning (DRL) based mobility load balancing (MLB) algorithm along with a two-layer architecture to solve the large-scale load balancing problem for ultra-dense networks (UDNs). Our contribution is three-fold. First, this work proposes a two-layer architecture to solve the…

We study Smoothed Online Convex Optimization, a version of online convex optimization where the learner incurs a penalty for changing her actions between rounds. Given a $Ω(\sqrt{d})$ lower bound on the competitive ratio of any online algorithm, where $d$ is the dimension of the action space, we ask under what conditio…

This paper explores how balancing and filtering techniques affect predictive multiplicity in machine learning models.

FairACE improves fairness in GNNs by balancing node performance across degree groups.

Active learning method improves AI performance by balancing exploration and exploitation.

New meta-learning method improves domain generalization by balancing parameters closer to domain centroids.

BalLOT uses optimal transport for balanced k-means clustering.

Study constructs balanced datasets for seismic failure prediction.

Proposes a method to balance tasks in multitask learning with a single gradient step update.

A new algorithm speeds up rerandomization for better experiment balance.

Spectral Clustering as a relaxation of the normalized/ratio cut has become one of the standard graph-based clustering methods. Existing methods for the computation of multiple clusters, corresponding to a balanced $k$-cut of the graph, are either based on greedy techniques or heuristics which have weak connection to th…

This study introduces balanced DRPS and OrderedLogitNN for better QDE of discrete-level questions.

BOSS learns from one labeled sample per class to match fully supervised performance.

SVM used for estimating treatment effects without confounding.

We test a historical price time series in a financial market (the NASDAQ 100 index) for a statistical property known as detailed balance. The presence of detailed balance would imply that the market can be modeled by a stochastic process based on a Markov chain, thus leading to equilibrium. In economic terms, a positiv…

TOPPO improves PPO for MTRL by balancing critic gradients, outperforming SAC.

We develop an efficient sampling method by simulating Langevin dynamics with an artificial force rather than a natural force by using the gradient of the potential energy. The standard technique for sampling following the predetermined distribution such as the Gibbs-Boltzmann one is performed under the detailed balance…

A new random forest algorithm improves tree construction for optimal performance.

The paper addresses classification imbalance by framing it as a transfer learning problem.

Transfer learning has achieved promising results by leveraging knowledge from the source domain to annotate the target domain which has few or none labels. Existing methods often seek to minimize the distribution divergence between domains, such as the marginal distribution, the conditional distribution or both. Howeve…

In this paper, we propose a novel technique to implement stochastic gradient methods, which are beneficial for learning from large datasets, through accelerated stochastic dynamics. A stochastic gradient method is based on mini-batch learning for reducing the computational cost when the amount of data is large. The sto…

Study reveals class disparities in balanced datasets through spectral imbalance.

Proposes a new framework for balancing average- and worst-case performance in machine learning.

In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally balances exploration and exploitation. In practice, however, EEM-based algorithms employ various approximations due to the computational ha…

Variational inference improves training of generative flow networks.

TempBalance boosts model performance with low data.

Proposes a novel neural network method to estimate average treatment effect.

This paper visualizes uncertainty in classifier performance metrics.

The ability to rank candidate architectures is the key to the performance of neural architecture search~(NAS). One-shot NAS is proposed to reduce the expense but shows inferior performance against conventional NAS and is not adequately stable. We investigate into this and find that the ranking correlation between archi…

Novel characterization of augmented balancing weights combining outcome and weighting models.

Balance corrects biased survey data for more accurate insights.