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.
New protocols show 1-bit mean estimation can be order-optimal without interaction.
Paper develops an efficient mean estimator for 1-bit communication constraints.
Paper proposes a 1-bit mean estimation method with near-optimal sample complexity.
New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.
Paper proposes a 1-bit quantization scheme for high-dimensional statistical estimation.
Paper analyzes BIHT for noisy 1-bit CS, improving results with up to τ-fraction of incorrect measurements.
A new method for 1-bit matrix completion that is faster and more accurate.
New method predicts binary matrix entries using empirical Bayes and low-rank structure.
We consider the problem of noisy 1-bit matrix completion under an exact rank constraint on the true underlying matrix . Instead of observing a subset of the noisy continuous-valued entries of a matrix , we observe a subset of noisy 1-bit (or binary) measurements generated according to a probabilistic model. W…
Study quantile reward identification with 1-bit feedback constraints.
Study improves fractional posterior for 1-bit matrix completion.
We consider in this paper the problem of noisy 1-bit matrix completion under a general non-uniform sampling distribution using the max-norm as a convex relaxation for the rank. A max-norm constrained maximum likelihood estimate is introduced and studied. The rate of convergence for the estimate is obtained. Information…
Paper offers robust recovery for 1-bit sensing with partial Gaussian circulant matrices.
Matrix completion has a long-time history of usage as the core technique of recommender systems. In particular, 1-bit matrix completion, which considers the prediction as a ``Recommended'' or ``Not Recommended'' question, has proved its significance and validity in the field. However, while customers and products aggre…
The goal of standard 1-bit compressive sensing is to accurately recover an unknown sparse vector from binary-valued measurements, each indicating the sign of a linear function of the vector. Motivated by recent advances in compressive sensing with generative models, where a generative modeling assumption replaces the u…
We present DeepFPC, a novel deep neural network designed by unfolding the iterations of the fixed-point continuation algorithm with one-sided l1-norm (FPC-l1), which has been proposed for solving the 1-bit compressed sensing problem. The network architecture resembles that of deep residual learning and incorporates pri…
The recent framework of compressive statistical learning aims at designing tractable learning algorithms that use only a heavily compressed representation-or sketch-of massive datasets. Compressive K-Means (CKM) is such a method: it estimates the centroids of data clusters from pooled, non-linear, random signatures of …
Paper tackles 1-bit compressed sensing, presenting efficient algorithm for sparse signal estimation.
For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when this requirement is imposed. Here, we report large improvements in error rates …
Binary Iterative Hard Thresholding converges with optimal number of 1-bit measurements.
Social trust prediction addresses the significant problem of exploring interactions among users in social networks. Naturally, this problem can be formulated in the matrix completion framework, with each entry indicating the trustness or distrustness. However, there are two challenges for the social trust problem: 1) t…
Recently, there is a growing interest in the study of median-based algorithms for distributed non-convex optimization. Two prominent such algorithms include signSGD with majority vote, an effective approach for communication reduction via 1-bit compression on the local gradients, and medianSGD, an algorithm recently pr…
Moniqua improves SGD convergence with quantized communication.
Paper studies signal detection in noisy environments with limited communication.
The paper develops a robust signal estimation method for noisy measurements from generative models.
Due to challenging applications such as collaborative filtering, the matrix completion problem has been widely studied in the past few years. Different approaches rely on different structure assumptions on the matrix in hand. Here, we focus on the completion of a (possibly) low-rank matrix with binary entries, the so-c…
Study on recovering sparse linear classifiers from mixed binary responses.
Autoencoders fail to capture sparse structure in 1-bit data compression.
Study on recovering supports of multiple sparse vectors from mixed linear measurements.
Unified framework for uniform signal recovery in nonlinear GCS with 1-bit/quantized measurements.
New model analyzes customer churn with tensor completion and binary data.
Communication overhead is a major bottleneck hampering the scalability of distributed machine learning systems. Recently, there has been a surge of interest in using gradient compression to improve the communication efficiency of distributed neural network training. Using 1-bit quantization, signSGD with majority vote …
This paper finds a unique partition of a sample space for estimating continuous distributions.
We study channel number reduction in combination with weight binarization (1-bit weight precision) to trim a convolutional neural network for a keyword spotting (classification) task. We adopt a group-wise splitting method based on the group Lasso penalty to achieve over 50% channel sparsity while maintaining the netwo…
We develop a new model and algorithms for machine learning-based learning analytics, which estimate a learner's knowledge of the concepts underlying a domain, and content analytics, which estimate the relationships among a collection of questions and those concepts. Our model represents the probability that a learner p…
The Straight-Through Estimator (STE) is widely used for back-propagating gradients through the quantization function, but the STE technique lacks a complete theoretical understanding. We propose an alternative methodology called alpha-blending (AB), which quantizes neural networks to low-precision using stochastic grad…
This paper introduces a differentiable, scalable quantization method for neural networks.
Implementing large-scale deep neural networks with high computational complexity on low-cost IoT devices may inevitably be constrained by limited computation resource, making the devices hard to respond in real-time. This disjunction makes the state-of-art deep learning algorithms, i.e. CNN (Convolutional Neural Networ…
BiTAT improves neural network quantization for edge devices by focusing on weight dependencies and disentangling them.
Optimal distributed testing under communication constraints with shared randomness.
In this paper, we propose a test, called Flagged-1-Bit (F1B) test, to study the intrinsic capability of recurrent neural networks in sequence learning. Four different recurrent network models are studied both analytically and experimentally using this test. Our results suggest that in general there exists a conflict be…
This paper resolves BIHT convergence, showing normalization is not necessary in noiseless settings but crucial for robustness.
For the efficient execution of deep convolutional neural networks (CNN) on edge devices, various approaches have been presented which reduce the bit width of the network parameters down to 1 bit. Binarization of the first layer was always excluded, as it leads to a significant error increase. Here, we present the novel…
New method approximates M-estimator and predictions without solving fixed-point equations.
New estimator reduces kernel mean estimation error.
New collaborative algorithm improves personalized mean estimation in online settings.
Low-bit training framework reduces energy consumption in CNNs.
Novel mean estimation method under user-level differential privacy reduces noise in continual mean estimates.