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.
AuxiLearn combines auxiliary tasks into a single loss function.
Proposes a method to improve graph neural networks on heterogeneous graphs using meta-paths.
New bounds for transfer learning in linear models, improving generalization.
Aux-NAS uses auxiliary labels to improve primary task performance without extra inference cost.
Learning with auxiliary tasks can improve the ability of a primary task to generalise. However, this comes at the cost of manually labelling auxiliary data. We propose a new method which automatically learns appropriate labels for an auxiliary task, such that any supervised learning task can be improved without requiri…
Efficiently optimize expensive functions using auxiliary task information.
Graph Neural Network (GNN) is a popular architecture for the analysis of chemical molecules, and it has numerous applications in material and medicinal science. Current lines of GNNs developed for molecular analysis, however, do not fit well on the training set, and their performance does not scale well with the comple…
NeurT-FDR controls FDR by incorporating auxiliary covariates in deep learning.
We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for training the lower layers of the network. During the network training, we seek an auxiliary loss that drives the lower layer to mimic the behavior …
Bayesian deep learning improves geostatistical mapping with auxiliary data.
WEEND uses a neural network to recognize speech and assign speakers to words.
Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged b…
Conventional application of convolutional neural networks (CNNs) for image classification and recognition is based on the assumption that all target classes are equal(i.e., no hierarchy) and exclusive of one another (i.e., no overlap). CNN-based image classifiers built on this assumption, therefore, cannot take into ac…
We propose a Multi-Task Learning (MTL) paradigm based deep neural network architecture, called MTCNet (Multi-Task Crowd Network) for crowd density and count estimation. Crowd count estimation is challenging due to the non-uniform scale variations and the arbitrary perspective of an individual image. The proposed model …
SXL embeds spatial autocorrelation into neural networks for better geographic data learning.
LDF combines neural networks with probabilistic models for data fusion.
Recent work has noted that all bad local minima can be removed from neural network loss landscapes, by adding a single unit with a particular parameterization. We show that the core technique from these papers can be used to remove all bad local minima from any loss landscape, so long as the global minimum has a loss o…
Variational inference for latent variable models is prevalent in various machine learning problems, typically solved by maximizing the Evidence Lower Bound (ELBO) of the true data likelihood with respect to a variational distribution. However, freely enriching the family of variational distribution is challenging since…
New method reduces neural network memorization of noisy labels.
One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations. However, it is not always trivial to know if an auxiliary task will be helpful for the main task and when it could start hurting. We propose to use the cosine similarity be…
Speech enhancement improved by adapting to unknown speakers without auxiliary signals.
New algorithm trains generative networks using explicit optimal transport distances.
We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and straightforward to improve the approximation by employing normalizing flows…
CCAC calibrates DNN classifiers on OOD datasets by separating mis-classified samples.
Physics-guided neural network improves power flow analysis.
New algorithm samples neural network posteriors efficiently.
XMixup improves transfer learning accuracy by 1.9% with less training time.
Transforms conditional density estimation into a nonparametric regression problem.
Estimating the travel time of a path is of great importance to smart urban mobility. Existing approaches are either based on estimating the time cost of each road segment which are not able to capture many cross-segment complex factors, or designed heuristically in a non-learning-based way which fail to utilize the exi…
Novel neural network models quantify uncertainty for deep classifiers.
Topic-aware chatbot learns from NMF topic vectors.
We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient updates should be statistically indistinguishable from each other. We enforce this c…
In several natural language tasks, labeled sequences are available in separate domains (say, languages), but the goal is to label sequences with mixed domain (such as code-switched text). Or, we may have available models for labeling whole passages (say, with sentiments), which we would like to exploit toward better po…
Paper introduces a novel method for estimating model confidence in deep neural classifiers.
Deep neural networks improve two-sample testing.
nnLDA combines neural and probabilistic methods for better topic modeling with side information.
Lack of labeled training data is a major bottleneck for neural network based aspect and opinion term extraction on product reviews. To alleviate this problem, we first propose an algorithm to automatically mine extraction rules from existing training examples based on dependency parsing results. The mined rules are the…
Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifier are typically optimized such that outputs from the model over a set of input samples most closely…
Click-through rate (CTR) prediction is a critical task in online advertising systems. A large body of research considers each ad independently, but ignores its relationship to other ads that may impact the CTR. In this paper, we investigate various types of auxiliary ads for improving the CTR prediction of the target a…
Energy-efficient detection of natural errors in deep networks.
Motivated by the necessity for parameter efficiency in distributed machine learning and AI-enabled edge devices, we provide a general and easy to implement method for significantly reducing the number of parameters of Convolutional Neural Networks (CNNs), during both the training and inference phases. We introduce a si…
Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to very long sequences. This paper proposes a simple method that improves the ability …
The paper develops a computational method for efficient online filtering of diffusion processes.
New model improves MCMC efficiency and multi-modal distribution exploration.
FedAUX improves Federated Learning by better using unlabeled data.
Despite significant recent advances in deep neural networks, training them remains a challenge due to the highly non-convex nature of the objective function. State-of-the-art methods rely on error backpropagation, which suffers from several well-known issues, such as vanishing and exploding gradients, inability to hand…
One reflection suffices for orthogonal weights, reducing GPU usage.
New method uses neural networks to identify sources from limited data in complex systems.