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.
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.
Softmax cross-entropy optimizes mutual information in neural networks.
problem Understanding the relationship between mutual information and classification neural networks.
method Demonstrated that optimizing softmax cross-entropy maximizes mutual information between inputs and labels.
result Softmax cross-entropy can approximate mutual information and highlight relevant image regions.
Develops RF-softmax for faster training with softmax cross entropy.
problem High computational cost of training with softmax cross entropy.
method Random Fourier Features for efficient sampling from approximate softmax distribution.
result RF-softmax provides low bias in estimating both softmax distribution and its gradient.
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.
Improved CNN for HCCR with new loss function and ranking method.
problem Loss of inter-class information in traditional CNN models for HCCR.
method Combining cross entropy with a new similarity ranking function (Average variance similarity) as loss function.
result New loss function (SoftMax cross entropy with Average variance similarity) achieves highest accuracy in HCCR.
A new method speeds up SoftMax normalization for embedding learning.
problem Efficiently learning distributed representations with SoftMax normalization.
method Proposes a linear-time heuristic approximation for mSoftMax(XYT), optimizing cross entropy. result Achieves higher or comparable accuracy to existing methods with lower computational time.
New insights into CE dynamics reveal how Hadamard initialization simplifies softmax.
problem Understanding the dynamics of cross-entropy training loss in deep learning.
method Analyzing a two-layer linear neural network with standard-basis vectors as inputs.
result Gradient flow on cross-entropy converges to neural collapse geometry, proving global convergence.
Recently, fully-connected and convolutional neural networks have been trained to achieve state-of-the-art performance on a wide variety of tasks such as speech recognition, image classification, natural language processing, and bioinformatics. For classification tasks, most of these "deep learning" models employ the so…
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.
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.
Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a gene…
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.
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.
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.
The paper analyzes how well classes are separated in neural network feature space.
problem Understanding class separability in neural network feature space.
method Theoretical analysis of intra-class and inter-class distances in feature space.
result A lower bound for the probability of inter-class distance being greater than intra-class distance as a function of loss value.
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…
Bayesian approach improves neural network classification accuracy and uncertainty.
problem Overconfidence and lack of uncertainty in softmax for classification tasks.
method Model categorical probability using a random variable with a prior distribution.
result Consistent gains in generalization performance across multiple tasks.
We empirically investigate the (negative) expected accuracy as an alternative loss function to cross entropy (negative log likelihood) for classification tasks. Coupled with softmax activation, it has small derivatives over most of its domain, and is therefore hard to optimize. A modified, leaky version is evaluated on…
This work explains how linear representations in large language models arise from training objectives and gradient descent.
problem Understanding the origins of linear representations in large language models.
method A latent variable model to abstract and formalize concept dynamics, combined with analysis of the softmax cross-entropy objective and gradient descent.
result Linear representations emerge when learning from data matching the latent variable model, and this simple structure suffices to yield linear representations.
The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks. In many applications such as language models or text generation, this model has to produce distributions over large output vocabularies. Recently, this has been shown to have limited repres…
Theoretical analysis of cross-entropy loss functions and their robustness.
problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First H-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses. Previous work shows that adversarially robust generalization requires larger sample complexity, and the same dataset, e.g., CIFAR-10, which enables good standard accuracy may not suffice to train robust models. Since collecting new training data could be costly, we focus on better utilizing the given data by inducing t…
Gradient flow in softmax models tends to produce low-entropy outputs.
problem Understanding the training dynamics of softmax-based models.
method Analysis of gradient flow dynamics in the value-softmax model.
result Gradient flow drives optimization towards low-entropy solutions.
Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are compact while the embeddings of samples of different categories are spread-out i…
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.
Gated Recurrent Unit (GRU) is a recently-developed variation of the long short-term memory (LSTM) unit, both of which are types of recurrent neural network (RNN). Through empirical evidence, both models have been proven to be effective in a wide variety of machine learning tasks such as natural language processing (Wen…
Entropy regularization improves policy optimization in reinforcement learning.
problem Improving policy optimization in reinforcement learning.
method Entropy regularization is introduced to soften the greedy policy towards a more diverse softmax policy, leading to a continuously parameterized algorithm that interpolates between policy gradient and Q-learning.
result An intermediate algorithm can improve performance in reinforcement learning.
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.
Softmax policy gradient methods converge at O(1/t) rate with constants depending on problem and initialization.
problem Understanding convergence rates of softmax policy gradient methods in tabular settings.
method Analysis of softmax policy gradient and entropy regularized policy gradient methods, using Łojasiewicz inequality and lower bounds.
result Entropy regularization improves convergence rate from O(1/t) to O(e−c⋅t). 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.
A new loss function improves neural networks' out-of-distribution detection without side effects.
problem Neural networks struggle with out-of-distribution detection due to SoftMax loss issues.
method Proposes IsoMax loss replacing SoftMax loss, maintaining high entropy and fast inferences.
result Significantly improves neural networks' out-of-distribution detection performance.
Softmax policy gradient achieves global optimality in wide neural networks with entropy regularization.
problem Optimizing softmax policies with neural networks in the mean-field regime.
method Modeling neural networks as Wasserstein gradient flows and proving global optimality of fixed points.
result Global optimality of softmax policy gradient in wide single hidden layer neural networks with entropy regularization.
A common practice in most of deep convolutional neural architectures is to employ fully-connected layers followed by Softmax activation to minimize cross-entropy loss for the sake of classification. Recent studies show that substitution or addition of the Softmax objective to the cost functions of support vector machin…
Improves uncertainty estimation and OOD detection in neural networks.
problem Accurate uncertainty estimation and OOD detection in neural networks.
method Investigates one-vs-all and distance-based logit representations for probabilities.
result One-vs-all formulations improve calibration without additional complexity.
Chronicals boosts LLM fine-tuning speed by 3.51x over Unsloth.
problem Memory bottleneck in fine-tuning large language models.
method Four optimizations: fused kernels, cross-entropy reduction, LoRA+, and sequence packing.
result 3.51x speedup on A100-40GB with Qwen2.5-0.5B.
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…
Simplified plug-in loss approximates EDL for reliable uncertainty estimation.
problem Efficient and reliable uncertainty estimation in real-world sensor-based learning systems.
method Approximate Dirichlet expected objectives with plug-in losses evaluated at the Dirichlet mean.
result Plug-in losses provide comparable predictive accuracy and selective prediction performance to classical EDL, while being simpler to implement.
Logit dynamics formula reveals self-regulation in softmax policy gradient methods.
problem Understanding the stability and convergence of softmax policy gradient methods.
method Deriving the exact formula for the L2 norm of the logit update vector.
result Logit update magnitudes are modulated by action probability and policy concentration.
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.
Study quantifies how LLMs capture higher-order statistical structure using cumulant expansion.
problem Understanding how LLMs internalize statistical structure during next-token prediction.
method Cumulant-expansion framework treating softmax entropy as perturbation around center distribution.
result Cumulants reveal distinct signatures for mathematical vs. general text prompts, quantifying feature-learning dynamics.
This work compares and evaluates various sampling methods for neural language models.
problem Lack of systematic comparison and myths about sampling methods.
method Monte Carlo sampling, importance sampling, compensated partial summation, noise contrastive estimation.
result All sampling methods can perform equally well if posterior probabilities are corrected.
Transformers model contextual relations using probabilistic measures, revealing their expressive power.
problem Lack of clear understanding of Transformer's ability to model contextual relations.
method Introduced a measure-theoretic framework connecting softmax attention and entropy-regularized optimal transport.
result Transformer architectures can approximate arbitrary contextual relations, and the choice of normalization affects how these relations are represented.
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that softmax consistent action values correspond to optimal entropy regularized policy pro…
Loss assigns examples to classes and superclasses in hierarchical data.
problem Learning from hierarchical classification problems with known class hierarchy.
method Introduces a loss function that considers the hierarchy of classes, aiming for consistent classification across different granularities.
result Improves accuracy and reduces coarse errors in classification compared to cross-entropy loss.
As deep learning methods form a critical part in commercially important applications such as autonomous driving and medical diagnostics, it is important to reliably detect out-of-distribution (OOD) inputs while employing these algorithms. In this work, we propose an OOD detection algorithm which comprises of an ensembl…
Focal loss reduces model curvature for better calibration.
problem Improving model confidence in classification problems.
method Geometric interpretation of focal loss to reduce curvature.
result Focal loss reduces the curvature of the loss surface, enhancing model calibration.
New loss improves OOD detection without extra data or tuning.
problem Improving OOD detection without additional data or tuning.
method Proposed IsoMax loss and entropic score to replace SoftMax loss.
result Training with IsoMax loss significantly improves OOD detection performance.