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.
Optimizes MCMC output compression by selecting a subset of states.
Bayesian classification and regression with high order interactions is largely infeasible because Markov chain Monte Carlo (MCMC) would need to be applied with a great many parameters, whose number increases rapidly with the order. In this paper we show how to make it feasible by effectively reducing the number of para…
Proposes SHORE model for efficient MOR with sparsity and scalability.
New method merges MCMC samples without distributional assumptions.
In this manuscript we propose two objective terms for neural image compression: a compression objective and a cycle loss. These terms are applied on the encoder output of an autoencoder and are used in combination with reconstruction losses. The compression objective encourages sparsity and low entropy in the activatio…
We compress large neural networks for quick adaptation to specific contexts.
A CAE improves DNN's outlier and adversary defense.
Regularized Stein thinning improves MCMC output approximations.
Markov chain Monte Carlo (MCMC) methods have not been broadly adopted in Bayesian neural networks (BNNs). This paper initially reviews the main challenges in sampling from the parameter posterior of a neural network via MCMC. Such challenges culminate to lack of convergence to the parameter posterior. Nevertheless, thi…
Proposes GPLFR for predicting high-dimensional outputs with few data.
As an alternative to variable selection or shrinkage in high dimensional regression, we propose to randomly compress the predictors prior to analysis. This dramatically reduces storage and computational bottlenecks, performing well when the predictors can be projected to a low dimensional linear subspace with minimal l…
Unified approach for robust low rank matrix estimation with adversaries.
We present a filter pruning approach for deep model compression, using a multitask network. Our approach is based on learning a a pruner network to prune a pre-trained target network. The pruner is essentially a multitask deep neural network with binary outputs that help identify the filters from each layer of the orig…
New insights into image compression trade-offs with private randomness.
We study and provide exposition to several phenomena that are related to the perceptron's compression. One theme concerns modifications of the perceptron algorithm that yield better guarantees on the margin of the hyperplane it outputs. These modifications can be useful in training neural networks as well, and we demon…
New SGD variant makes neural networks compressible without assumptions.
Develops a new MCMC-based Wishart prior for Gaussian Process covariance matrix.
New compression theory justifies model pruning for neural networks.
It is well known that Markov chain Monte Carlo (MCMC) methods scale poorly with dataset size. A popular class of methods for solving this issue is stochastic gradient MCMC. These methods use a noisy estimate of the gradient of the log posterior, which reduces the per iteration computational cost of the algorithm. Despi…
Bayesian data sketching speeds up inference for large functional data.
Paper introduces vector-valued variation spaces for multi-output neural networks.
The paper provides privacy guarantees for MCMC algorithms using Langevin dynamics.
In Divide & Recombine (D&R), big data are divided into subsets, each analytic method is applied to subsets, and the outputs are recombined. This enables deep analysis and practical computational performance. An innovate D\&R procedure is proposed to compute likelihood functions of data-model (DM) parameters for big dat…
Paper compresses ViTs models by 60% with minimal accuracy loss.
Turbo-DDCM speeds up zero-shot image compression.
SeReNe prunes neurons with low sensitivity to reduce network size.
Novel compression method preserves privacy while reducing communication costs.
A new shrinkage-based construction is developed for a compressible vector , for cases in which the components of $\xv$ are naturally associated with a tree structure. Important examples are when $\xv$ corresponds to the coefficients of a wavelet or block-DCT representation of data. The me…
Long Short-Term Memory (LSTM) is one of the most widely used recurrent structures in sequence modeling. It aims to use gates to control information flow (e.g., whether to skip some information or not) in the recurrent computations, although its practical implementation based on soft gates only partially achieves this g…
Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and security issues. As a compromise between privacy and performance, in this paper we inve…
Boosting improves accuracy by combining weak learners into a voting classifier.
Particle MCMC is a class of algorithms that can be used to analyse state-space models. They use MCMC moves to update the parameters of the models, and particle filters to propose values for the path of the state-space model. Currently the default is to use random walk Metropolis to update the parameter values. We show …
Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to better utilize the available spatial diversity and multiplexing gains. However, in a frequency division duplex (FDD) massive MIMO system, CSI feedback overhead degrades the overall spectral…
A simple and widely adopted approach to extend Gaussian processes (GPs) to multiple outputs is to model each output as a linear combination of a collection of shared, unobserved latent GPs. An issue with this approach is choosing the number of latent processes and their kernels. These choices are typically done manuall…
Data-independent pruning method reduces neural network size with accuracy guarantees.
MoDeGPT compresses large language models without accuracy loss, saving 98% compute costs.
We present an efficient coresets-based neural network compression algorithm that sparsifies the parameters of a trained fully-connected neural network in a manner that provably approximates the network's output. Our approach is based on an importance sampling scheme that judiciously defines a sampling distribution over…
A new method for compressive classification using bridge regression.
Kernel methods summarize and integrate posterior similarity matrices from Bayesian clustering.
New algorithm optimizes MCMC sampling for structural dynamic models.
Knowledge distillation (KD) is a popular method for reducing the computational overhead of deep network inference, in which the output of a teacher model is used to train a smaller, faster student model. Hint training (i.e., FitNets) extends KD by regressing a student model's intermediate representation to a teacher mo…
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there is a need for compression techniques that can achieve significant compression wit…
ChEES-HMC improves SMC samplers' efficiency and speed.
Unified bounds linking compressibility, fractal dimensions, and mutual information.
Recently, multilayer bootstrap network (MBN) has demonstrated promising performance in unsupervised dimensionality reduction. It can learn compact representations in standard data sets, i.e. MNIST and RCV1. However, as a bootstrap method, the prediction complexity of MBN is high. In this paper, we propose an unsupervis…
This paper studies how to compress neural networks while maintaining accuracy.
End-to-end meta-learned system for image compression.
IoT nodes compress measurements into DNN outputs for efficient communication.