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.
This work compresses sequences by treating them as continuous-time processes, enabling efficient discretization.
A framework infers causal direction from symbolic sequences using compression measures.
Proposes a method to train neural networks directly on compressed text data.
We present the Compressive Transformer, an attentive sequence model which compresses past memories for long-range sequence learning. We find the Compressive Transformer obtains state-of-the-art language modelling results in the WikiText-103 and Enwik8 benchmarks, achieving 17.1 ppl and 0.97 bpc respectively. We also fi…
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling approach to compress temporal sequences with a focus on video. Our approach builds upon…
We discuss algorithms for estimating the Shannon entropy h of finite symbol sequences with long range correlations. In particular, we consider algorithms which estimate h from the code lengths produced by some compression algorithm. Our interest is in describing their convergence with sequence length, assuming no limit…
New compression methods handle biased input sequences for more accurate posterior summaries.
Funnel-Transformer reduces computation by compressing sequence data.
Paper compresses RNNs using HT decomposition for better performance.
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…
Video analytics requires operating with large amounts of data. Compressive sensing allows to reduce the number of measurements required to represent the video using the prior knowledge of sparsity of the original signal, but it imposes certain conditions on the design matrix. The Bayesian compressive sensing approach r…
We propose and analyze an online algorithm for reconstructing a sequence of signals from a limited number of linear measurements. The signals are assumed sparse, with unknown support, and evolve over time according to a generic nonlinear dynamical model. Our algorithm, based on recent theoretical results for -$…
Extractive compression is a challenging natural language processing problem. This work contributes by formulating neural extractive compression as a parse tree transduction problem, rather than a sequence transduction task. Motivated by this, we introduce a deep neural model for learning structure-to-substructure tree …
For a real or complex semisimple Lie group and two nested parabolic subgroups , we study parabolic geometries of type . Associated to the group , we introduce a class of relative natural bundles and relative tractor bundles and construct some basic invariant differential operators on …
This paper introduces matrix product state (MPS) decomposition as a new and systematic method to compress multidimensional data represented by higher-order tensors. It solves two major bottlenecks in tensor compression: computation and compression quality. Regardless of tensor order, MPS compresses tensors to matrices …
Neural NCD reveals LLMs don't compress well for classification.
A new memory-efficient sign language translation model reduces weight usage.
We analyze the mapping class group of extendible automorphisms of the exterior boundary W of a compression body of dimension 3 or 4, which extend over the compression body (Q,V), where V is the interior boundary. Those that extend as automorphisms of (Q,V) rel V are called discrepant automorphisms, forming the mapping …
New algorithm reduces communication in distributed learning by sharing compressed beliefs.
Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently represent and reconstruct a video sequence from its missing or under-sampled measuremen…
Prior work inspired by compression algorithms has described how the Burrows Wheeler Transform can be used to create a distance measure for bioinformatics problems. We describe issues with this approach that were not widely known, and introduce our new Burrows Wheeler Markov Distance (BWMD) as an alternative. The BWMD a…
Paper proposes a compression principle for neural networks using Bayesian optimization.
We consider a decomposition method for compressive streaming data in the context of online compressive Robust Principle Component Analysis (RPCA). The proposed decomposition solves an - cluster-weighted minimization to decompose a sequence of frames (or vectors), into sparse and low-rank components, from com…
Global Memory Augmentation (GMAT) improves Transformer performance on long documents.
We consider a compact orientable hyperbolic 3-manifold with a compressible boundary. Suppose that we are given a sequence of geometrically finite hyperbolic metrics whose conformal boundary structures at infinity diverge to a projective lamination. We prove that if this limit projective lamination is doubly incompressi…
Image compression techniques reveal network structure for shipping box optimization.
Express improves causal attention guarantees for language models.
Sparsity-based approaches have been popular in many applications in image processing and imaging. Compressed sensing exploits the sparsity of images in a transform domain or dictionary to improve image recovery from undersampled measurements. In the context of inverse problems in dynamic imaging, recent research has de…
PCNN prunes CNN weights efficiently for hardware acceleration.
Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bottle-neck in memory constraint on-device training applications like federated learning and on-device inference applications like automatic spe…
The paper analyzes geometric densities and compression radii for knot types.
We consider lossless compression based on statistical data modeling followed by prediction-based encoding, where an accurate statistical model for the input data leads to substantial improvements in compression. We propose DZip, a general-purpose compressor for sequential data that exploits the well-known modeling capa…
WildCat efficiently compresses neural network attention mechanisms.
New bounds for large language models using token properties.
Generates high-quality images using sparse DCT representations.
Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters throug…
We propose a generalization of neural network sequence models. Instead of predicting one symbol at a time, our multi-scale model makes predictions over multiple, potentially overlapping multi-symbol tokens. A variation of the byte-pair encoding (BPE) compression algorithm is used to learn the dictionary of tokens that …
This paper describes a new online convex optimization method which incorporates a family of candidate dynamical models and establishes novel tracking regret bounds that scale with the comparator's deviation from the best dynamical model in this family. Previous online optimization methods are designed to have a total a…
Learning to remember long sequences remains a challenging task for recurrent neural networks. Register memory and attention mechanisms were both proposed to resolve the issue with either high computational cost to retain memory differentiability, or by discounting the RNN representation learning towards encoding shorte…
Computer simulations have become a popular tool of assessing complex skills such as problem-solving skills. Log files of computer-based items record the entire human-computer interactive processes for each respondent. The response processes are very diverse, noisy, and of nonstandard formats. Few generic methods have b…
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…
R2T hybrid model improves robust regression for asymmetric noise.
New adapted renormalized volume for hyperbolic 3-manifolds with compressible boundary.
Midicoth compresses online probability estimates by correcting prior smoothing biases.
Context-aware recommender systems (CARSs) apply sensing and analysis of user context in order to provide personalized services. Adding context to a recommendation model is challenging, since the addition of context may increases both the dimensionality and sparsity of the model. Recent research has shown that modeling …
Stable long-term predictions for fluid flows using neural networks.
In this paper, we compare various methods to compress a text using a neural model. We find that extracting tokens as latent variables significantly outperforms the state-of-the-art discrete latent variable models such as VQ-VAE. Furthermore, we compare various extractive compression schemes. There are two best-performi…
Detection of rare variants by resequencing is important for the identification of individuals carrying disease variants. Rapid sequencing by new technologies enables low-cost resequencing of target regions, although it is still prohibitive to test more than a few individuals. In order to improve cost trade-offs, it has…