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.
Paper analyzes trade-offs in top-k classification accuracies and proposes a new loss function.
DeepTopPush improves accuracy at the top for complex classification tasks.
Extends linear classification framework to nonlinear SVM-based ranking problems.
A new hierarchical forecasting method improves overall accuracy.
A framework for binary classification on top samples.
Work on making classifiers robust against adversarial attacks for top-k predictions.
Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.
Unified model for prediction and deferral selects top-k entities efficiently.
Efficient algorithm for evaluating hierarchical classification methods at multiple operating points.
OverQ increases model accuracy by handling outliers in neural networks with minimal hardware changes.
Top-k sparsification reduces deep learning communication costs.
Improved chemical reaction prediction using augmented NLP models.
Class ambiguity is typical in image classification problems with a large number of classes. When classes are difficult to discriminate, it makes sense to allow k guesses and evaluate classifiers based on the top-k error instead of the standard zero-one loss. We propose top-k multiclass SVM as a direct method to optimiz…
New scoring rules compare probabilistic top lists in classification.
Photo-identification (photo-id) of dolphin individuals is a commonly used technique in ecological sciences to monitor state and health of individuals, as well as to study the social structure and distribution of a population. Traditional photo-id involves a laborious manual process of matching each dolphin fin photogra…
Developing neural network image classification models often requires significant architecture engineering. In this paper, we study a method to learn the model architectures directly on the dataset of interest. As this approach is expensive when the dataset is large, we propose to search for an architectural building bl…
Large-scale classification of data where classes are structurally organized in a hierarchy is an important area of research. Top-down approaches that exploit the hierarchy during the learning and prediction phase are efficient for large scale hierarchical classification. However, accuracy of top-down approaches is poor…
For information retrieval and binary classification, we show that precision at the top (or precision at k) and recall at the top (or recall at k) are maximised by thresholding the posterior probability of the positive class. This finding is a consequence of a result on constrained minimisation of the cost-sensitive exp…
The importance of accurate recommender systems has been widely recognized by academia and industry. However, the recommendation quality is still rather low. Recently, a linear sparse and low-rank representation of the user-item matrix has been applied to produce Top-N recommendations. This approach uses the nuclear nor…
A new method for efficiently updating large-scale matrices in real-time.
The paper addresses calibration in label ranking, a structured prediction task.
In designing personalized ranking algorithms, it is desirable to encourage a high precision at the top of the ranked list. Existing methods either seek a smooth convex surrogate for a non-smooth ranking metric or directly modify updating procedures to encourage top accuracy. In this work we point out that these methods…
Negative user preference is an important context that is not sufficiently utilized by many existing recommender systems. This context is especially useful in scenarios where the cost of negative items is high for the users. In this work, we describe a new recommender algorithm that explicitly models negative user prefe…
In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weig…
Paper introduces algorithms for private decision tree learning.
Paper introduces a new loss function for deep imbalanced classification.
Convolutional neural networks (CNNs) are commonly trained using a fixed spatial image size predetermined for a given model. Although trained on images of aspecific size, it is well established that CNNs can be used to evaluate a wide range of image sizes at test time, by adjusting the size of intermediate feature maps.…
Nonlinear conjugate gradient (NLCG) based optimizers have shown superior loss convergence properties compared to gradient descent based optimizers for traditional optimization problems. However, in Deep Neural Network (DNN) training, the dominant optimization algorithm of choice is still Stochastic Gradient Descent (SG…
We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems. The LML layer provides a probabilistic way of modeling multi-label predictions limited to having exactly k labels. We derive efficient forward and backward passes for this layer and show how the layer…
Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained devices. Existing compression techniques, while excelling at reducing model sizes, struggle to be comp…
Synchronized stochastic gradient descent (SGD) optimizers with data parallelism are widely used in training large-scale deep neural networks. Although using larger mini-batch sizes can improve the system scalability by reducing the communication-to-computation ratio, it may hurt the generalization ability of the models…
BitPruning learns optimal bitlengths for neural networks to balance accuracy and efficiency.
Top-N recommender systems have been investigated widely both in industry and academia. However, the recommendation quality is far from satisfactory. In this paper, we propose a simple yet promising algorithm. We fill the user-item matrix based on a low-rank assumption and simultaneously keep the original information. T…
Decision tree learning is a popular approach for classification and regression in machine learning and statistics, and Bayesian formulations---which introduce a prior distribution over decision trees, and formulate learning as posterior inference given data---have been shown to produce competitive performance. Unlike c…
Predict accuracy of neural architectures using non-neural models.
Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time. In this …
Study improves forecasting of aggregated curves in electricity markets.
Automatic sleep staging has been often treated as a simple classification problem that aims at determining the label of individual target polysomnography (PSG) epochs one at a time. In this work, we tackle the task as a sequence-to-sequence classification problem that receives a sequence of multiple epochs as input and…
IITK wins FinSim 2020 task on financial hypernym detection.
Motivated by applications in recommender systems, web search, social choice and crowdsourcing, we consider the problem of identifying the set of top items from noisy pairwise comparisons. In our setting, we are non-actively given pairwise comparisons between each pair of items, where each comparison has noi…
Paper extends top-k Mallows model for better user preference analysis.
A new multi-phase approach improves supply chain forecasting accuracy.
Study on top- classification with new loss functions and algorithms.
New method improves accuracy of quantized neural networks.
Avian Influenza breakouts cause millions of dollars in damage each year globally, especially in Asian countries such as China and South Korea. The impact magnitude of a breakout directly correlates to time required to fully understand the influenza virus, particularly the interspecies pathogenicity. The procedure requi…
New method makes CNN interpretations robust to adversarial attacks.
Stock return forecasting is of utmost importance in the business world. This has been the favourite topic of research for many academicians since decades. Recently, regularization techniques have reported to tremendously increase the forecast accuracy of the simple regression model. Still, this model cannot incorporate…
Minimalistic unsupervised learning with sparse manifold transform achieves SOTA performance.