arXiv research

High error rates improve neural network performance and reduce power consumption.

RAMs improve GAMs' accuracy by fitting components to subregions of feature space.

Dropout and RaM become equivalent in large ResNets as depth and width increase.

Federated Learning tackles limited user participation with a new risk-aware approach.

RAM extends attention-based mechanism for existence determination.

Memory-augmented neural networks consisting of a neural controller and an external memory have shown potentials in long-term sequential learning. Current RAM-like memory models maintain memory accessing every timesteps, thus they do not effectively leverage the short-term memory held in the controller. We hypothesize t…

Improves bit error tolerance in RRAM-based BNNs without overfitting.

This paper optimizes SMPC for neural network inference, reducing memory and time.

The paper studies causal effects of multiple treatments in healthcare databases with rare outcomes.

Regression problems that have closed-form solutions are well understood and can be easily implemented when the dataset is small enough to be all loaded into the RAM. Challenges arise when data is too big to be stored in RAM to compute the closed form solutions. Many techniques were proposed to overcome or alleviate the…

This paper compares FAISS and FENSHSES for nearest neighbor search in Hamming space.

We introduce an exact distributed algorithm to train Random Forest models as well as other decision forest models without relying on approximating best split search. We explain the proposed algorithm and compare it to related approaches for various complexity measures (time, ram, disk, and network complexity analysis).…

This paper investigates compression techniques for deep neural networks to reduce their size without sacrificing performance.

In this paper, a taxonomy for memory networks is proposed based on their memory organization. The taxonomy includes all the popular memory networks: vanilla recurrent neural network (RNN), long short term memory (LSTM ), neural stack and neural Turing machine and their variants. The taxonomy puts all these networks und…

For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference. Completely avoiding inference-time floating-point operations is one of the simplest ways to design …

This paper investigates whether learning contingency-awareness and controllable aspects of an environment can lead to better exploration in reinforcement learning. To investigate this question, we consider an instantiation of this hypothesis evaluated on the Arcade Learning Element (ALE). In this study, we develop an a…

Multidimensional time series are sequences of real valued vectors. They occur in different areas, for example handwritten characters, GPS tracking, and gestures of modern virtual reality motion controllers. Within these areas, a common task is to search for similar time series. Dynamic Time Warping (DTW) is a common di…

Penalized regression models such as the lasso have been extensively applied to analyzing high-dimensional data sets. However, due to memory limitations, existing R packages like glmnet and ncvreg are not capable of fitting lasso-type models for ultrahigh-dimensional, multi-gigabyte data sets that are increasingly seen …

Bayesian realized EGARCH models improve tail risk forecasting.

SNG-DBSCAN clusters data faster with subsampled similarity queries.

Develops a Riemannian archetypal analysis for interpretable non-linear data.

Bayesian Neural Networks (BNNs) have been proposed to address the problem of model uncertainty in training and inference. By introducing weights associated with conditioned probability distributions, BNNs are capable of resolving the overfitting issue commonly seen in conventional neural networks and allow for small-da…

Big T-Rex solves FDR-controlled sparse regression on laptops with millions of variables.

In real world industrial applications of topic modeling, the ability to capture gigantic conceptual space by learning an ultra-high dimensional topical representation, i.e., the so-called "big model", is becoming the next desideratum after enthusiasms on "big data", especially for fine-grained downstream tasks such as …

This paper enables deep network inference on microcontrollers with improved accuracy and reduced memory usage.

Improved deep learning model deployment on tiny MCUs with mixed-precision quantization.

The $k$-Nearest Neighbor Search ($k$-NNS) is the backbone of several cloud-based services such as recommender systems, face recognition, and database search on text and images. In these services, the client sends the query to the cloud server and receives the response in which case the query and response are revealed t…