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…
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.
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.
New neural network approach using mutual information.
problem Training neural networks for imbalanced datasets.
method Converts neural network classifiers to mutual information evaluators.
result New form of softmax leads to better classification accuracy, especially for imbalanced datasets.
Proposes a method to solve deep neural networks' local minimum problem.
problem Local minimum problem in deep neural networks training.
method Transforms cross-entropy loss into risk-averse error criterion, adjusts RSI, and uses convexity region.
result Trained deep learning machine is expected to be inside a global minimum's attraction basin.
Paper proposes AXE loss for non-autoregressive machine translation, improving performance.
problem Challenges in training non-autoregressive models due to lack of autoregressive factors and cross entropy loss penalties.
method Proposes aligned cross entropy (AXE) loss function using a differentiable dynamic program for better word order alignment.
result AXE-based training improves performance on major WMT benchmarks and sets a new state of the art for non-autoregressive models.
Proposes squentropy loss for improved classification accuracy and model calibration.
problem Theoretical and empirical evidence for cross-entropy loss is lacking.
method Introduces squentropy loss as the sum of cross-entropy and average square loss over incorrect classes.
result Squentropy loss outperforms cross-entropy and rescaled square losses in classification accuracy and model calibration.
In deep neural network, the cross-entropy loss function is commonly used for classification. Minimizing cross-entropy is equivalent to maximizing likelihood under assumptions of uniform feature and class distributions. It belongs to generative training criteria which does not directly discriminate correct class from co…
Two things seem to be indisputable in the contemporary deep learning discourse: 1. The categorical cross-entropy loss after softmax activation is the method of choice for classification. 2. Training a CNN classifier from scratch on small datasets does not work well. In contrast to this, we show that the cosine loss fun…
We present the Tamed Cross Entropy (TCE) loss function, a robust derivative of the standard Cross Entropy (CE) loss used in deep learning for classification tasks. However, unlike other robust losses, the TCE loss is designed to exhibit the same training properties than the CE loss in noiseless scenarios. Therefore, th…
This paper shows using classification instead of regression improves deep RL scalability.
problem Challenges in training value functions for large networks in deep RL.
method Used categorical cross-entropy loss instead of mean squared error regression.
result Significant improvements in performance and scalability across various domains.
Paper proposes a new loss function for conditional models using soft targets.
problem Improving generalization performance of deep neural networks on supervised classification tasks.
method Introduces a new loss function compatible with soft targets, based on noise contrastive estimation.
result Soft target InfoNCE loss performs on par with cross-entropy baselines and outperforms other losses.
ANTIDOTE reduces noisy labels influence during learning.
problem Learning with noisy labels.
method Information-divergence neighborhood relaxation and adversarial training.
result ANTIDOTE outperforms standard cross-entropy loss in noisy label settings.
Generative Cross-Entropy improves classification with fewer labels.
problem Limited sample efficiency of cross-entropy loss in data-scarce scenarios.
method Proposes Generative Cross-Entropy (GenCE), a new loss function that incorporates generative principles into a standard discriminative network.
result Generative Cross-Entropy outperforms traditional cross-entropy loss across various datasets and conditions.
Develops a mean-field theory for multi-head self-attention under cross-entropy training.
problem Mean-field analysis of multi-head self-attention under cross-entropy training.
method Mean-field theory for a simplified single-layer causal multi-head self-attention model.
result Proves a static finite-head approximation bound for the optimal risk.
We extend recent work (Brehmer, et. al., 2018) that use neural networks as surrogate models for likelihood-free inference. As in the previous work, we exploit the fact that the joint likelihood ratio and joint score, conditioned on both observed and latent variables, can often be extracted from an implicit generative m…
Proposes SOVR loss to improve adversarial robustness by increasing logit margins.
problem Adversarial training's difficulty in robustness against sophisticated attacks.
method Introduces SOVR loss function that switches from cross-entropy to one-vs-the-rest loss for important samples.
result SOVR loss increases logit margins of important samples, improving robustness against Auto-Attack.
Pre-training improves model coverage, crucial for downstream performance.
problem Understanding why pre-training enhances model performance.
method Coverage principle, focusing on next-token prediction and model quality.
result Coverage generalizes faster than cross-entropy, improving downstream performance.
New method controls classifier guidance in diffusion models.
problem Improving classifier guidance in diffusion models.
method Cross-entropy control of classifier gradients.
result Effective guidance vectors with mean squared error O(dε). State-of-the-art neural networks are vulnerable to adversarial examples; they can easily misclassify inputs that are imperceptibly different than their training and test data. In this work, we establish that the use of cross-entropy loss function and the low-rank features of the training data have responsibility for th…
Loss functions play a crucial role in deep metric learning thus a variety of them have been proposed. Some supervise the learning process by pairwise or tripletwise similarity constraints while others take advantage of structured similarity information among multiple data points. In this work, we approach deep metric l…
EAST aligns neural network classifiers with user-defined evaluation metrics.
problem Mismatch between neural network training and evaluation metrics leads to suboptimal performance.
method EAST uses dynamic thresholding, soft-set confusion matrix, and annealing to align neural network predictions with target evaluation metrics.
result EAST improves alignment between training objectives and evaluation metrics, outperforming existing methods.
In this paper, we present a machine learning approach for estimating the number of incident wavefronts in a direction of arrival scenario. In contrast to previous works, a multilayer neural network with a cross-entropy objective is trained. Furthermore, we investigate an online training procedure that allows an adaptio…
This work shows that supervised contrastive learning achieves similar results to cross-entropy but requires more iterations.
problem The question of whether there are fundamental differences in representation geometry between supervised contrastive learning and cross-entropy.
method The authors prove that both losses attain their minimum when representations of each class collapse to the vertices of a regular simplex, and they empirically validate this finding.
result Supervised contrastive learning requires more iterations to reach a close-to-optimal state compared to cross-entropy, indicating different optimization behavior.
Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalization may improve practical applications of deep networks. In this paper we show that with cross-entropy loss it is surprisingly simple to ind…
This research improves neural network uncertainty estimates and reliability.
problem Lack of inherent uncertainty estimates and variability in softmax scores.
method Ensemble-based Dirichlet modeling with method of moments estimator.
result Improved stability and predictive uncertainty estimates.
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.
The empirical NTK diverges from the NTK in classification problems during overtraining.
problem The divergence of empirical NTK from NTK in classification problems during overtraining.
method Demonstrated strictly positive definiteness of NTKs for FCNs and ResNets. Proved divergence of neural network parameters during training with cross-entropy loss.
result The empirical NTK does not uniformly converge to the NTK across all times on the training samples as the network width increases.
We introduce the HSIC (Hilbert-Schmidt independence criterion) bottleneck for training deep neural networks. The HSIC bottleneck is an alternative to the conventional cross-entropy loss and backpropagation that has a number of distinct advantages. It mitigates exploding and vanishing gradients, resulting in the ability…
In this paper, we focus on the separability of classes with the cross-entropy loss function for classification problems by theoretically analyzing the intra-class distance and inter-class distance (i.e. the distance between any two points belonging to the same class and different classes, respectively) in the feature s…
This work improves adversarial robustness by boosting model ensembles with margin maximization.
problem Single models are insufficient for defending against adversarial attacks.
method Margin-boosting approach to learn ensembles with maximum margin.
result Our algorithm outperforms existing ensembling techniques and large models trained end-to-end.
New analysis shows how cross-entropy training shapes attention in transformers.
problem Understanding how gradient-based learning creates the required internal geometry in transformers.
method Developed a first-order analysis of cross-entropy training effects on attention scores and values in a transformer attention head.
result Introduced an advantage-based routing law and responsibility-weighted update for attention scores and values, respectively.
This paper extends neural collapse to class-imbalanced datasets using an unconstrained ReLU feature model.
problem Understanding neural collapse in class-imbalanced datasets with cross-entropy loss.
method Generalized neural collapse to class-imbalanced settings using an unconstrained ReLU feature model.
result Class-means converge to orthogonal vectors with different lengths, and classifier weights align to these vectors.
Paper tackles long-tailed labels in classification problems.
problem Imbalanced or long-tailed label distribution in real-world classification problems.
method Logit adjustment applied post-hoc or during training to encourage a large relative margin between rare and dominant labels.
result Unified and generalised techniques for coping with long-tailed labels, improving generalisation and performance.
New ACE cost function encourages diversity in neural networks.
problem Training multiple classifiers with controlled diversity.
method Mathematical derivation and gradient control.
result ACE yields better ensemble results than vanilla.
Training accurate deep neural networks (DNNs) in the presence of noisy labels is an important and challenging task. Though a number of approaches have been proposed for learning with noisy labels, many open issues remain. In this paper, we show that DNN learning with Cross Entropy (CE) exhibits overfitting to noisy lab…
This paper extends neural collapse to imbalanced data under cross-entropy loss.
problem Analyzing neural collapse in deep networks with imbalanced data.
method Using the unconstrained feature model and cross-entropy loss, the paper studies neural collapse in imbalanced datasets.
result Feature vectors within the same class collapse to a single mean vector, but angles between them depend on sample size.
Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the training distribution where the observed distribution changes is also fundamentally important to achieve a more powerful form of generaliza…
When humans learn a new concept, they might ignore examples that they cannot make sense of at first, and only later focus on such examples, when they are more useful for learning. We propose incorporating this idea of tunable sensitivity for hard examples in neural network learning, using a new generalization of the cr…
Learning with a primary objective, such as softmax cross entropy for classification and sequence generation, has been the norm for training deep neural networks for years. Although being a widely-adopted approach, using cross entropy as the primary objective exploits mostly the information from the ground-truth class f…
Study shows MSE with sigmoid can match SCE in classification tasks, especially with noisy data.
problem Inconsistent errors in neural network classification tasks.
method Introduced Output Reset algorithm to use MSE with sigmoid activation.
result MSE with sigmoid activation achieves comparable accuracy and convergence rates to Softmax Cross-Entropy, especially in noisy data scenarios.
Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by utilizing adversarial training or model distillation, which adds additional procedure…
LLMs learn peaked distributions slowly due to power-law losses.
problem Slow convergence of loss in training large language models.
method Systematic analysis of toy models and empirical evaluation of LLMs.
result Power-law time scaling with an exponent of 1/3 for learning peaked distributions.
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 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.
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.
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.
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.