A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Novel loss function improves few-shot classification performance.
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…
In a multi-class classification problem, it is standard to model the output of a neural network as a categorical distribution conditioned on the inputs. The output must therefore be positive and sum to one, which is traditionally enforced by a softmax. This probabilistic mapping allows to use the maximum likelihood pri…
Paper explains learning property of logistic and softmax losses for balanced and imbalanced class data.
A new loss function improves neural networks' out-of-distribution detection without side effects.
In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation, two fields that fall into the framework of learning from Positive and Unlabeled d…
Unified interpretation of softmax cross-entropy and negative sampling for knowledge graph embedding.
The computational cost of training with softmax cross entropy loss grows linearly with the number of classes. For the settings where a large number of classes are involved, a common method to speed up training is to sample a subset of classes and utilize an estimate of the loss gradient based on these classes, known as…
Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has produced promising results to tackle the mentioned task. To train deep learning systems, the loss function is essential to the network performa…
Despite being the standard loss function to train multi-class neural networks, the log-softmax has two potential limitations. First, it involves computations that scale linearly with the number of output classes, which can restrict the size of problems we are able to tackle with current hardware. Second, it remains unc…
We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities. After deriving its properties, we show how its Jacobian can be efficiently computed, enabling its use in a network trained with backpropagation. Then, we propose a new smooth and convex loss func…
Bayesian approach improves neural network classification accuracy and uncertainty.
Out-of-distribution (OOD) detection approaches usually present special requirements (e.g., hyperparameter validation, collection of outlier data) and produce side effects (e.g., classification accuracy drop, slower energy-inefficient inferences). We argue that these issues are a consequence of the SoftMax loss anisotro…
Evidential Softmax preserves multimodality in sparse probability distributions for generative models.
Paper introduces Balanced Meta-Softmax for better long-tailed visual recognition.
Introduces gradient decay in Softmax for better generalization.
In many scenarios of a language identification task, the user will specify a small set of languages which he/she can speak instead of a large set of all possible languages. We want to model such prior knowledge into the way we train our neural networks, by replacing the commonly used softmax loss function with a novel …
Simplified plug-in loss approximates EDL for reliable uncertainty estimation.
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…
In order to push the performance on realistic computer vision tasks, the number of classes in modern benchmark datasets has significantly increased in recent years. This increase in the number of classes comes along with increased ambiguity between the class labels, raising the question if top-1 error is the right perf…
Computations for the softmax function are significantly expensive when the number of output classes is large. In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes. Different from most…
Solves challenges in estimating parameters of softmax gating Gaussian mixture models.
Convolution Neural Networks (CNN) have recently achieved state-of-the art performance on handwritten Chinese character recognition (HCCR). However, most of CNN models employ the SoftMax activation function and minimize cross entropy loss, which may cause loss of inter-class information. To cope with this problem, we pr…
Gradient flow in softmax models tends to produce low-entropy outputs.
New neural network approach using mutual information.
New insights into CE dynamics reveal how Hadamard initialization simplifies softmax.
LLMs learn peaked distributions slowly due to power-law losses.
This research improves neural network uncertainty estimates and reliability.
The Softmax function is used in the final layer of nearly all existing sequence-to-sequence models for language generation. However, it is usually the slowest layer to compute which limits the vocabulary size to a subset of most frequent types; and it has a large memory footprint. We propose a general technique for rep…
Gradient flow on softmax attention minimizes nuclear norm of weight matrices.
A new method for optimizing regression problems with ReLU units converges.
Deep convolutional neural networks (CNNs) can be applied to malware binary detection via image classification. The performance, however, is degraded due to the imbalance of malware families (classes). To mitigate this issue, we propose a simple yet effective weighted softmax loss which can be employed as the final laye…
A new method speeds up SoftMax normalization for embedding learning.
Study on multi-head softmax attention dynamics for in-context learning.
Unified scheme combining softmax and ResNet for deep learning.
This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the recognition of emotion in speech. Speech features such as Spectrograms and Mel-freq…
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…
New insights into the top-K sparse softmax gating function for deep learning.
Focal loss reduces model curvature for better calibration.
Study examines Lasso performance in high-dimensional MoE models.
Improved similarity search in embeddings using InfoNCE loss.
Balanced Activation improves object detection performance on long-tailed datasets.
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…
Study on learning to defer to multiple experts with consistent surrogates and confidence calibration.
When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference. For example, in sequence-to-sequence modeling we are interested in high-quality translated sentences, but training typically uses maximum likelihood at the word level. The…
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…
Efficient algorithm for evaluating hierarchical classification methods at multiple operating points.
Loss assigns examples to classes and superclasses in hierarchical data.