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.
DFRot improves LLMs by reducing outlier and massive activation effects.
Training examples are not all equally informative. Active learning strategies leverage this observation in order to massively reduce the number of examples that need to be labeled. We leverage the same observation to build a generic strategy for parallelizing learning algorithms. This strategy is effective because the …
In this paper, we investigate the geometric structure of activation spaces of fully connected layers in neural networks and then show applications of this study. We propose an efficient approximation algorithm to characterize the convex hull of massive points in high dimensional space. Based on this new algorithm, four…
Paper speeds up IoT device detection and data decoding.
We consider the problem of learning classifiers for labeled data that has been distributed across several nodes. Our goal is to find a single classifier, with small approximation error, across all datasets while minimizing the communication between nodes. This setting models real-world communication bottlenecks in the …
Social activities play an important role in people's daily life since they interact. For recommendations based on social activities, it is vital to have not only the activity information but also individuals' social relations. Thanks to the geo-social networks and widespread use of location-aware mobile devices, massiv…
Deep active learning aims to reduce annotation costs while leveraging DL's powerful learning.
Data collection at a massive scale is becoming ubiquitous in a wide variety of settings, from vast offline databases to streaming real-time information. Learning algorithms deployed in such contexts must rely on single-pass inference, where the data history is never revisited. In streaming contexts, learning must also …
A new criterion for deep active learning selects minimal labeled data points.
Understanding the spatiotemporal distribution of people within a city is crucial to many planning applications. Obtaining data to create required knowledge, currently involves costly survey methods. At the same time ubiquitous mobile sensors from personal GPS devices to mobile phones are collecting massive amounts of d…
RAN model recognizes multiple activities from unlabeled sensor data.
New algorithms learn from comparisons to classify data robustly to noise.
A fundamental aspect of biological information processing is the ubiquity of sequence-function relationships -- functions that map the sequence of DNA, RNA, or protein to a biochemically relevant activity. Most sequence-function relationships in biology are quantitative, but only recently have experimental techniques f…
The Web has enabled one of the most visible recent developments in education---the deployment of massive open online courses. With their global reach and often staggering enrollments, MOOCs have the potential to become a major new mechanism for learning. Despite this early promise, however, MOOCs are still relatively u…
The splendid success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, in medical imaging, it is challenging to create such large annotated datasets, as annotating medical images is not only tedious…
Deep learning models can overfit noisy data without losing generalization.
Machine Learning (ML) is making a strong resurgence in tune with the massive generation of unstructured data which in turn requires massive computational resources. Due to the inherently compute- and power-intensive structure of Neural Networks (NNs), hardware accelerators emerge as a promising solution. However, with …
Efficient algorithms identify true hypothesis from many options with minimal actions.
Deep learning reduces training overhead in massive MIMO systems.
Modeling influenza spread using feature engineering and international flow deconvolution.
Massive fermions help understand index theorems without chiral symmetry.
In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. I…
This work bridges continual learning, active learning, and open set recognition in deep neural networks.
Efficient algorithm reduces communication costs in sparse regression.
Deep nets with massive data learn spatially sparse functions.
Random orthogonalization improves FL in massive MIMO systems without CSI.
A new framework for coreset selection in machine learning models.
The performance of classification algorithms with a massive and highly imbalanced data stream depends upon efficient balancing strategy. Some techniques of balancing strategy have been applied in the past with Batch data to resolve the class imbalance problem. This paper proposes a new incremental data balancing framew…
Efficiently bootstraps massive distributed data without over-resampling.
Optimizes lockdown strategies to balance economic activities and virus spread.
Small sample size hinders accurate long-term COVID-19 case predictions.
Study evaluates topological contributions in massive SQCD on compact 4-manifolds.
Massively multi-label prediction/classification problems arise in environments like health-care or biology where very precise predictions are useful. One challenge with massively multi-label problems is that there is often a long-tailed frequency distribution for the labels, which results in few positive examples for t…
Unified framework for photon and massive particle hypersurfaces in stationary spacetimes.
Transferability of learned features between tasks can massively reduce the cost of training a neural network on a novel task. We investigate the effect of network width on learned features using activation atlases --- a visualization technique that captures features the entire hidden state responds to, as opposed to in…
New algorithms for fair data summarization in massive data models.
In this work we simulate null geodesics for the Bonnor massive dipole metric by implementing a symbolic-numerical algorithm in Sage and Python. This program is also capable of visualizing in 3D, in principle, the geodesics for any given metric. Geodesics are launched from a common point, collectively forming a cone of …
One major challenge in training Deep Neural Networks is preventing overfitting. Many techniques such as data augmentation and novel regularizers such as Dropout have been proposed to prevent overfitting without requiring a massive amount of training data. In this work, we propose a new regularizer called DeCov which le…
Develops a new theory for approximating functions on massive data.
Introduces a massive variant of Ray-Singer Torsion to avoid zero modes in topological field theories.
New method for efficient inference in large datasets.
This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels. When represented in appropriate domains, massive MIMO channels have a sparse structure which can be efficiently learned by CNNs for positioning …
QEM uses parallel importance weighting for fast approximate Bayesian inference.
VTIRT speeds up IRT inference for dynamic learner proficiency.
Study improves scalability of cell-free massive MIMO networks by optimizing UE-AP association.
We present a Bayesian non-negative tensor factorization model for count-valued tensor data, and develop scalable inference algorithms (both batch and online) for dealing with massive tensors. Our generative model can handle overdispersed counts as well as infer the rank of the decomposition. Moreover, leveraging a repa…
Neural MMO simulates MMOs to study multiagent intelligence.
Knowledge distillation is an effective technique that transfers knowledge from a large teacher model to a shallow student. However, just like massive classification, large scale knowledge distillation also imposes heavy computational costs on training models of deep neural networks, as the softmax activations at the la…