Proposes JBNN for multi-label classification with improved efficiency and performance.
problem Multi-label classification with dependencies and heavy computational load.
method Joint Binary Neural Network (JBNN) that synchronously performs multiple binary classifications and captures label relations via joint binary cross entropy (JBCE) loss.
result Significantly better performance and computational efficiency compared to state-of-the-art methods.
Improved cross-entropy estimator for likelihood-free inference.
problem Efficient inference for complex models with intractable likelihoods.
method Use neural networks as surrogate models and augment training data with joint likelihood ratio and score.
result New cross-entropy estimator provides improved sample efficiency.
This paper reformulates Fβ for better model performance and interpretation.
problem Optimizing model performance and interpretation using Fβ metric. method Reformulate Fβ metric to facilitate statistical distributions and dynamic penalty weights. result Better and interpretable results with a 14% boost in F1 score for IMDB data. New methods improve Bayesian inference and decision-making in online learning.
problem Current Bayesian deep learning does not fully utilize joint predictives for sequential decision-making.
method Proposes new evaluation settings for active learning and active sampling, focusing on marginal and joint cross-entropies.
result Initial experiments suggest challenges in applying current BDL inference techniques in high-dimensional spaces.
Modified AUC improves CNN training by considering model confidence.
problem Improving binary classifier performance metrics.
method Proposes a modified AUC metric that incorporates model confidence into BCE loss for CNN training.
result Demonstrates improved performance on three datasets: MNIST, prostate MRI, and brain MRI.
Paper optimizes score transformation for fair binary classification.
problem Ensuring fairness in binary classification with predicted scores.
method Formulates and solves a convex optimization problem for transforming scores to meet fairness constraints.
result Derives a closed-form expression for optimal transformed scores and provides guarantees for finite sample settings.
New neural network separates singing voices from music using cross entropy loss.
problem Separating singing voices from music accompaniment.
method Deep Convolutional Neural Network (CNN) trained with Ideal Binary Mask (IBM) and cross entropy loss.
result Proposed CNN outperforms existing systems in MIREX evaluations.
MIM learns joint distributions with mutual information and low divergence.
problem Learning joint distributions over observations and latent variables.
method Probabilistic auto-encoder with three design principles: low divergence, high mutual information, and low marginal entropy.
result MIM learns representations with high mutual information, consistent encoding and decoding distributions, effective latent clustering, and comparable data log likelihood to VAE.
Improves GAN training by guiding the discriminator to have more diverse binary activation patterns.
problem Stability and convergence issues in GAN training.
method Binarized Representation Entropy (BRE) regularization to guide the discriminator's model capacity allocation.
result Improves GAN training stability and convergence speed, higher sample quality, and higher classification accuracy.
Improved speaker verification with condition-aware backend.
problem Speaker verification calibration issues under unknown conditions.
method Discriminative PLDA model with joint training and condition integration.
result Out-of-the-box excellent calibration performance.
This study uses Tsallis entropy to analyze diversification and integration in Italian stock market companies.
problem Examining the industrial structure and market reactions of cross-shareholding networks.
method Developed Tsallis entropy approach to model diversification and integration using copulas.
result Entropy analysis reveals insights into market polarisation and fairness.
A new method uses deep learning to predict full conditional distributions.
problem Lack of uncertainty information in conditional distribution predictions.
method Transformed distribution estimation into multi-class classification, using deep neural networks and a joint binary cross-entropy loss function.
result Improved accuracy in probabilistic solar energy forecasting.
This work extends implicit bias analysis to multiclass classification using a new loss framework.
problem The implicit bias of gradient descent on multiclass data without explicit regularization.
method Employing the PERM framework to introduce a multiclass extension of the exponential tail property.
result Extended implicit bias result to multiclass classification using a new loss framework.
DAEs trained to minimize BCE can move data samples towards higher probability regions.
problem Improving data samples by moving them towards higher probability regions.
method Training DAEs to minimize binary cross-entropy (BCE).
result Iterative application of trained DAEs moves data samples from low to high probability regions.
In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling th…
A new method is proposed to compute connectivity measures on multivariate time series with gaps. Rather than removing or filling the gaps, the rows of the joint data matrix containing empty entries are removed and the calculations are done on the remainder matrix. The method, called measure adapted gap removal (MAGR), …
EDLP samples flat modes in discrete spaces using entropy.
problem Sampling flat modes in discrete spaces is challenging.
method EDLP uses a continuous auxiliary variable and local entropy to guide sampling.
result EDLP consistently outperforms traditional methods in various tasks.
Cubic predicts stock market indices by fusing stock latent embeddings and converting to binary classification.
problem Challenges in predicting stock market indices due to isolated time series treatment and simple regression.
method Fusion of stock latent embeddings, binary encoding classification, and confidence-guided prediction.
result Cubic outperforms state-of-the-art baselines in stock index prediction tasks.
In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling th…
The paper explores how different loss functions impact reinforcement learning algorithms.
problem Improving reinforcement learning algorithms by optimizing loss functions.
method Comprehensive survey on loss functions in reinforcement learning, proving the benefits of specific loss functions.
result Binary cross-entropy loss leads to first-order bounds and is more efficient than squared loss.
Optimizes binary regression models with gradient ascent-descent methods.
problem Regression problems with binary weights in quantized learning and digital communication.
method Maximin optimization using gradient ascent-descent methods.
result The approach is optimal in linear regression with low noise and robust regression with few outliers.
New training scheme reduces adversarial examples by increasing decision boundary margin.
problem Vulnerability of neural networks to adversarial examples.
method Differential training using a loss function on feature differences.
result Differential training significantly reduces adversarial examples.
Paper proposes mutual information learning for deep learning classifiers.
problem Overfitting in deep learning models.
method Mutual information learning framework to train classifiers.
result MILCs achieve better generalization than conditional entropy classifiers.
Machine learning for entropy calculation from binary signals.
problem Calculating entropy from binary configurations/signals.
method Transformed entropy calculation into supervised classification tasks using machine learning.
result Reproduced entropy and free energy of the 2D Ising model.
The study analyzes multi-class teacher-student perceptron performance and generalization errors.
problem Analyzing multi-class classification with the teacher-student perceptron.
method Deriving asymptotic expressions for Bayes-optimal and empirical risk minimization (ERM) generalization errors.
result Regularised cross-entropy minimization yields close-to-optimal accuracy for multi-class classification.
JES optimizes expensive functions by considering joint entropy over input and output spaces.
problem Optimizing expensive functions with limited evaluations.
method Joint Entropy Search (JES) considers joint entropy over input and output spaces.
result JES outperforms other information-theoretic methods in Bayesian optimization.
Transformer pre-training improves stock return prediction accuracy.
problem Improving stock price prediction accuracy for better investment decisions.
method Pre-trained transformer models on TSX index, fine-tuned for individual stocks, compared to LSTM and XGBoost.
result Transformer model achieved lower mean squared error than benchmarks.
Quantum machine learning uses quantum cross entropy to minimize loss, but measurement loss affects this process.
problem Quantum machine learning's loss minimization through cross entropy is affected by measurement outcomes.
method Defined quantum cross entropy, proved its lower bounds, and investigated its relation to quantum fidelity and likelihood.
result Quantum cross entropy is lower-bounded by negative log-likelihood when derived from quantum data, but measurement outcomes can cause loss.
This paper uses copulas and entropies to analyze cross-shareholding configurations in stock markets.
problem Analyzing the concentration and integration of companies in cross-shareholding networks.
method The approach combines copula theory and entropy measures to study the stochastic dependence of diversification and integration.
result The copula approach reveals the dependence structure leading to market polarization or fairness.
The paper presents a method to estimate joint interventional distributions from marginal interventional data.
problem Estimating joint interventional distributions from marginal interventional data.
method The paper extends the Causal Maximum Entropy method to use interventional data and employs Lagrange duality to prove the solution lies in the exponential family.
result The method allows for causal feature selection and inference of joint interventional distributions.
New method identifies common cause in causal insufficiency, revealing complex phase transitions.
problem Identifying common cause in causal insufficiency with observed joint probability.
method Generalized maximum likelihood method, closely related to maximum entropy principle.
result Identifies consistent common cause that aligns with the common cause principle.
Cross-entropy loss linked to metric learning, outperforming complex pairwise losses.
problem Improving metric learning performance without complex optimization schemes.
method Theoretical analysis linking cross-entropy to pairwise losses, showing cross-entropy as an upper bound and equivalent to mutual information maximization.
result Minimizing cross-entropy is equivalent to maximizing mutual information, leading to state-of-the-art performance.
New loss functions improve extreme classification with missing labels.
problem Large number of infrequent labels and missing labels in XMC.
method Derive unbiased loss functions for XMC, incorporating them into existing algorithms.
result Significant improvement in extreme classification performance (up to 20%) over existing methods.
Unified approach to stabilize adversarial learning for joint distribution matching.
problem Non-identifiability issues in bidirectional adversarial training.
method Unified framework of adversarial and non-adversarial approaches, stabilizing learning.
result Stabilized learning of unsupervised and semi-supervised bidirectional adversarial methods.
Unified interpretation of softmax cross-entropy and negative sampling for knowledge graph embedding.
problem Lack of theoretical relationship between softmax cross-entropy and negative sampling loss functions in knowledge graph embedding.
method Used Bregman divergence to provide a unified interpretation of the two loss functions.
result Theoretical findings for fair comparison of softmax cross-entropy and negative sampling are derived.
In this paper, we propose majority voting neural networks for sparse signal recovery in binary compressed sensing. The majority voting neural network is composed of several independently trained feedforward neural networks employing the sigmoid function as an activation function. Our empirical study shows that a choice…
PAC-Bayesian bounds for MLPs with cross entropy loss validated.
problem Generalization bounds for MLPs with cross entropy loss.
method Introduced probabilistic explanations and proved PAC-Bayesian bounds using ELBO.
result MLPs with cross entropy loss inherently guarantee PAC-Bayesian generalization bounds.
Better signal detection in undersampled data using joint and cross covariances.
problem Detecting shared signals in high-dimensional data with limited samples.
method Analysis of three covariance matrices: individual, cross, and joint.
result Joint and cross covariance matrices detect signals earlier than individual covariances.
Tamed Cross Entropy (TCE) loss outperforms standard CE loss in noisy classification tasks.
problem Improving classification performance in noisy data scenarios.
method Introducing Tamed Cross Entropy (TCE) loss, a derivative of Cross Entropy (CE) loss.
result TCE loss outperforms CE loss in all tested noisy classification scenarios.
Unified approach optimizes neural network training for various metrics.
problem Training and evaluation of neural network binary classifiers often use different metrics.
method Combines differentiable approximation and probabilistic soft sets.
result Effective in optimizing for metrics like F1-Score across various domains.
New estimator for joint entropy outperforms existing methods in various distributions.
problem Estimating joint entropy in high-dimensional spaces.
method Partitioned sample spacing (PSS) for nonparametric estimation.
result PSS consistently outperforms k-NN and normalizing flow methods.
Study Transformer layers under cross-entropy training using mean field control.
problem Understanding the behavior of Transformer layers in cross-entropy training.
method Continuous-depth mean field control analysis, treating depth as time and layer parameters as controls.
result Derivation of a Pontryagin condition for the limiting population problem, involving the softmax residual.
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothin…
New method detects changes by maximizing cross-entropy, outperforming existing techniques.
problem Detecting abrupt changes in data streams without labeled examples.
method Maximizes cross-entropy between segments to find change points, using dynamic programming.
result Outperforms three state-of-the-art approaches on challenging datasets.
Square loss performs comparably or better than cross-entropy in neural architectures for various tasks.
problem The superiority of cross-entropy loss over square loss in classification tasks is debated.
method Comparison of several neural architectures on NLP, ASR, and computer vision datasets using both loss functions.
result Square loss often produces better results in the majority of tasks, especially in NLP and ASR.
New tree-based SVM methods for multi-class classification.
problem Efficient multi-class classification for large datasets.
method Entropy and generalization error estimation for binary classifiers in tree nodes.
result Proposed methods outperform traditional techniques in speed and accuracy.
Gradient descent aligns weights in deep linear networks for binary classification.
problem Aligning weights in deep linear networks for binary classification.
method Gradient descent applied to strictly decreasing loss functions.
result Normalized weight matrices align across layers, converging to the maximum margin solution.
The paper proposes a method to learn structured representations from unlabeled data using mutual information maximization.
problem Learning structured representations from unlabeled data.
method Adversarial maximization of mutual information between a structured latent variable and a target variable.
result The proposed method outperforms current baselines in document hashing and yields highly compressed interpretable representations.