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.
The bits-back argument suggests that latent variable models can be turned into lossless compression schemes. Translating the bits-back argument into efficient and practical lossless compression schemes for general latent variable models, however, is still an open problem. Bits-Back with Asymmetric Numeral Systems (BB-A…
Generalizes bits back coding for time-series models with latent Markov structures.
Deep latent variable models have seen recent success in many data domains. Lossless compression is an application of these models which, despite having the potential to be highly useful, has yet to be implemented in a practical manner. We present `Bits Back with ANS' (BB-ANS), a scheme to perform lossless compression w…
New method improves image compression using bits-back coding.
SHVC improves image compression with fewer parameters.
A new method, REC, compresses images by encoding their latent representations efficiently.
This paper simplifies ANS for statisticians, making it easier to use.
The state-of-the-art hardware platforms for training Deep Neural Networks (DNNs) are moving from traditional single precision (32-bit) computations towards 16 bits of precision -- in large part due to the high energy efficiency and smaller bit storage associated with using reduced-precision representations. However, un…
Likelihood-based generative models are the backbones of lossless compression due to the guaranteed existence of codes with lengths close to negative log likelihood. However, there is no guaranteed existence of computationally efficient codes that achieve these lengths, and coding algorithms must be hand-tailored to spe…
Reduced precision computation for deep neural networks is one of the key areas addressing the widening compute gap driven by an exponential growth in model size. In recent years, deep learning training has largely migrated to 16-bit precision, with significant gains in performance and energy efficiency. However, attemp…
Develops a method for lossless compression using latent variable models.
While deep neural networks are a highly successful model class, their large memory footprint puts considerable strain on energy consumption, communication bandwidth, and storage requirements. Consequently, model size reduction has become an utmost goal in deep learning. A typical approach is to train a set of determini…
ActNN reduces neural network training memory by 2-bit quantization.
Task offloading is an emerging technology in fog-enabled networks. It allows users to transmit tasks to neighbor fog nodes so as to utilize the computing resources of the networks. In this paper, we investigate a stochastic task offloading model and propose a multi-armed bandit framework to formulate this model. We con…
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…
Training convolutional neural network models is memory intensive since back-propagation requires storing activations of all intermediate layers. This presents a practical concern when seeking to deploy very deep architectures in production, especially when models need to be frequently re-trained on updated datasets. In…
MSD removes dequantization bottleneck in LLM inference by approximating high-precision activations.
This paper proposes a learning framework for n-bit quantized neural networks that improves accuracy and speed on FPGAs.
We make the following striking observation: fully convolutional VAE models trained on 32x32 ImageNet can generalize well, not just to 64x64 but also to far larger photographs, with no changes to the model. We use this property, applying fully convolutional models to lossless compression, demonstrating a method to scale…
New techniques improve 16-bit training accuracy without 32-bit units.
Bayesian Bits unifies quantization and pruning through gradient optimization.
Low-bit training framework reduces energy consumption in CNNs.
To make deep neural networks feasible in resource-constrained environments (such as mobile devices), it is beneficial to quantize models by using low-precision weights. One common technique for quantizing neural networks is the straight-through gradient method, which enables back-propagation through the quantization ma…
Paper improves DNN accelerator robustness against bit errors with energy savings.
Majority bit estimation in noisy random recursive DAGs.
Paper proposes a CNN-based method for estimating intra frame bits and quality.
Emerging resistive random-access memory (ReRAM) has recently been intensively investigated to accelerate the processing of deep neural networks (DNNs). Due to the in-situ computation capability, analog ReRAM crossbars yield significant throughput improvement and energy reduction compared to traditional digital methods.…
Improves matrix multiplication throughput for asymmetric bit-width operands.
In our previous work we have shown that resistive cross point devices, so called Resistive Processing Unit (RPU) devices, can provide significant power and speed benefits when training deep fully connected networks as well as convolutional neural networks. In this work, we further extend the RPU concept for training re…
New protocols show 1-bit mean estimation can be order-optimal without interaction.
Topological data analysis classifies encrypted bits with success.
We consider the problem of estimating the mean of a symmetric log-concave distribution under the constraint that only a single bit per sample from this distribution is available to the estimator. We study the mean squared error as a function of the sample size (and hence the number of bits). We consider three settings:…
Paper offers robust recovery for 1-bit sensing with partial Gaussian circulant matrices.
One-bit feedback suffices for a bandit problem's optimal strategy.
New algorithm tackles batched stochastic linear bandits with 1-bit communication constraints.
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…
Moniqua improves SGD convergence with quantized communication.
ADD embeds a 48-bit message into images, achieving high accuracy and speed.
This letter proposes a dictionary learning algorithm for blind one bit compressed sensing. In the blind one bit compressed sensing framework, the original signal to be reconstructed from one bit linear random measurements is sparse in an unknown domain. In this context, the multiplication of measurement matrix $\Ab$ an…
FleXOR trains fractional quantization for neural networks, improving accuracy and size.
Paper studies distributed learning with limited communication bits, achieving optimal error exponents.
WrapNet optimizes inference for low-resolution neural networks by using 8-bit additions.
The method of random projections has become a standard tool for machine learning, data mining, and search with massive data at Web scale. The effective use of random projections requires efficient coding schemes for quantizing (real-valued) projected data into integers. In this paper, we focus on a simple 2-bit coding …
Kernel Quantization improves CNN compression without sacrificing performance.
Minwise hashing is the standard technique in the context of search and databases for efficiently estimating set (e.g., high-dimensional 0/1 vector) similarities. Recently, b-bit minwise hashing was proposed which significantly improves upon the original minwise hashing in practice by storing only the lowest b bits of e…
Paper proposes a 1-bit quantization scheme for high-dimensional statistical estimation.
Bit threads provide an alternative description of holographic entanglement, replacing the Ryu-Takayanagi minimal surface with bulk curves connecting pairs of boundary points. We use bit threads to prove the monogamy of mutual information (MMI) property of holographic entanglement entropies. This is accomplished using t…
Study quantile reward identification with 1-bit feedback constraints.