To improve how neural networks function it is crucial to understand their learning process. The information bottleneck theory of deep learning proposes that neural networks achieve good generalization by compressing their representations to disregard information that is not relevant to the task. However, empirical evid…
On-device research index
arXiv research
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.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Functional Compression”
Compressive learning is a framework where (so far unsupervised) learning tasks use not the entire dataset but a compressed summary (sketch) of it. We propose a compressive learning classification method, and a novel sketch function for images.
Proposes a new linearity-based neural network compression method.
problem Reduction of neural network model size while maintaining accuracy.
method Integrates linearity-based intuition with ReLU activation functions to merge layers.
result Achieves up to 75% reduction in model size without loss of accuracy.
The enormous size of modern deep neural networks makes it challenging to deploy those models in memory and communication limited scenarios. Thus, compressing a trained model without a significant loss in performance has become an increasingly important task. Tremendous advances has been made recently, where the main te…
We obtain the first positive results for bounded sample compression in the agnostic regression setting with the loss, where . We construct a generic approximate sample compression scheme for real-valued function classes exhibiting exponential size in the fat-shattering dimension but independen…
Globally optimized SVD compression of LLMs via Fermi-function-based rank selection and gauge fixingcs.LG
Physics-inspired methods optimize SVD compression of LLMs.
problem Efficiently compressing large language models (LLMs) using SVD.
method FermiGrad for globally optimal rank selection and PivGa for lossless compression.
result Global optimization of SVD ranks and lossless compression of low-rank factors.
The Compressibility of Minimal Lattice Knotscond-mat.soft
The (isothermic) compressibility of lattice knots can be examined as a model of the effects of topology and geometry on the compressibility of ring polymers. In this paper, the compressibility of minimal length lattice knots in the simple cubic, face centered cubic and body centered cubic lattices are determined. Our r…
Learnable multiclass hypothesis classes don't always have a sample compression scheme of fixed size.
problem The limitation of sample compression schemes for multiclass hypothesis classes.
method Analysis of DS dimension and sample compression schemes.
result Learnable multiclass hypothesis classes do not always have a sample compression scheme of fixed size.
This paper develops a method to estimate the rate-distortion function for general data sources.
problem Estimating the rate-distortion function for general data sources.
method Develops an algorithm for sandwiching the R-D function of a general (not necessarily discrete) source using i.i.d. data samples.
result Estimates R-D sandwich bounds for various data sources, including natural images, indicating potential for improving compression methods.
Recurrent iterated function systems (RIFSs) are improvements of iterated function systems (IFSs) using elements of the theory of Marcovian stochastic processes which can produce more natural looking images. We construct new RIFSs consisting substantially of a vertical contraction factor function and nonlinear transform…
Data compression speeds up machine learning loss calculations.
problem Computational demand in calculating mean squared error for large datasets.
method Use rank-1 lattices to compress data, assigning weights based on original data and responses.
result Our QMC data compression algorithms can lead to arbitrary high convergence rates for smooth functions.
This paper improves the scalability of sparse neural network compression.
problem Sparse neural network compression for diverse data modalities.
method State-of-the-art sparsification techniques and meta-learning.
result Meta-learning sparse compression networks achieve new state-of-the-art results.
Model compression has been introduced to reduce the required hardware resources while maintaining the model accuracy. Lots of techniques for model compression, such as pruning, quantization, and low-rank approximation, have been suggested along with different inference implementation characteristics. Adopting model com…
COIN++ compresses multiple data types efficiently.
problem Handling diverse data modalities in neural compression.
method Implicit neural representations and modulations quantization.
result Significant compression gains with reduced encoding time.
Optimal Network Compressionq-fin.RM
Paper tackles optimal network compression for financial systems.
problem Optimal network compression for financial systems under shocks.
method Formulated as an NP-hard problem, studied systemic risk measures, and analyzed specific networks.
result Systemic fragility results no longer hold generally under shocks and heterogeneous networks.
Galen algorithm compresses neural networks for specific hardware with reduced latency.
problem Finding optimal compression policies for neural networks on specific hardware.
method Reinforcement learning using pruning and quantization to optimize inference latency.
result Compressed ResNet18 for ARM processor reduced inference latency by 80%.
This work proves that large models can be compressed significantly without losing performance.
problem Achieving comparable performance with smaller models and less data.
method Developed a universal compression theory for neural networks and datasets.
result Proved that a generic permutation-invariant function can be compressed into a function of polylogarithmic size with vanishing error.
The paper analyzes geometric densities and compression radii for knot types.
problem Optimizing geometric quantities associated with knot types.
method Develops a factorization framework for scale-covariant size functionals.
result Different minimizing sequences for density, compression, packing, and ropelength problems.
Reduces multiclass and regression compression schemes to binary ones.
problem Developing efficient learning algorithms for multiclass and regression problems.
method Reduces sample compression schemes for binary classes to multiclass and regression settings.
result Establishes new compression schemes for multiclass and regression problems.
This paper proposes a new method for efficient data compression using Bayesian neural networks.
problem Efficient compression of data represented as functions mapping coordinates to signal values.
method Overfitting variational Bayesian neural networks to the data and compressing an approximate posterior weight sample using relative entropy coding.
result Our method achieves strong performance on image and audio compression while retaining simplicity.
A Machine Learning Framework for Distributed Functional Compression over Wireless Channels in IoTcs.LG
A new machine learning framework reduces IoT data transfer by two orders of magnitude.
problem Reducing data transfer in IoT devices over wireless channels.
method Developed a machine learning framework for distributed functional compression over GMAC and AWGN channels.
result The framework reduces communication by two orders of magnitude compared to cloud-based methods.
Study robust regression learning under adversarial attacks.
problem Understanding which function classes are learnable in the presence of adversarial attacks.
method Introduced a novel agnostic sample compression scheme and used fat-shattering dimension to construct adversarially robust sample compression schemes.
result Finite fat-shattering dimension classes are learnable in both realizable and agnostic settings.
Autoencoders fail to capture sparse structure in 1-bit data compression.
problem Proving the performance of shallow autoencoders on sparse data compression.
method Gradient descent analysis and approximate message passing.
result Gradient descent minimizer for sparse data is the identity (up to permutation) above critical sparsity.
Modern neural networks are highly overparameterized, with capacity to substantially overfit to training data. Nevertheless, these networks often generalize well in practice. It has also been observed that trained networks can often be "compressed" to much smaller representations. The purpose of this paper is to connect…
New theory controls compression change probability without prior knowledge.
problem Controlling compression change probability without prior knowledge.
method New theory on compression function and statistical risk.
result Cardinality of compressed set is a consistent estimator of probability of change of compression.
As the industry deploys increasingly large and complex neural networks to mobile devices, more pressure is put on the memory and compute resources of those devices. Deep compression, or compression of deep neural network weight matrices, is a technique to stretch resources for such scenarios. Existing compression metho…
We show that the type function of a space with finite asymptotic dimension estimates its Hilbert (or any ) compression. The method allows to obtain the lower bound of the compression of the lamplighter group , which has infinite asymptotic dimension.
Generative networks trained with sketching reduce computational burden.
problem Computational expense of training generative networks on large datasets.
method Compressive learning using a single sketch vector to approximate Maximum Mean Discrepancy.
result Cost-efficient optimization of generative networks on large datasets.
New approach for learning large Bayesian networks using feature clustering and compression.
problem Learning large Bayesian networks efficiently and accurately.
method Feature space clustering, compression, and Hill-Climbing algorithm with BIC and MI score functions.
result Potential for parallelizable block learning and improved structure accuracy.
This letter proposes a sparse diffusion steepest-descent algorithm for one bit compressed sensing in wireless sensor networks. The approach exploits the diffusion strategy from distributed learning in the one bit compressed sensing framework. To estimate a common sparse vector cooperatively from only the sign of measur…
End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses reinforcement learning (RL) to optimize the per-layer compression ratios when applied to a state-of-the-art attention based end-to-end ASR mod…
In this draft, which reports on work in progress, we 1) adapt the information bottleneck functional by replacing the compression term by class-conditional compression, 2) relax this functional using a variational bound related to class-conditional disentanglement, 3) consider this functional as a training objective for…
We give an algorithmically efficient version of the learner-to-compression scheme conversion in Moran and Yehudayoff (2016). In extending this technique to real-valued hypotheses, we also obtain an efficient regression-to-bounded sample compression converter. To our knowledge, this is the first general compressed regre…
Properties of steady compressible flow for which geometric constraints have been placed on the potential function are derived, under hypotheses on the flow density and the singular set. Some related unconstrained problems are also considered, including the estimation of a class of fields having nonzero vorticity.
New method connects compression bodies through cone manifolds.
problem Understanding how compression bodies can be transformed.
method Using cone manifold holonomy groups and standard space techniques.
result Realized all edges in compression body graph through paths.
This paper aims at achieving a "good" estimator for the gradient of a function on a high-dimensional space. Often such functions are not sensitive in all coordinates and the gradient of the function is almost sparse. We propose a method for gradient estimation that combines ideas from Spall's Simultaneous Perturbation …
Compressed imitation learning uses simplicity priors for efficient expert behavior copying.
problem Efficiently learn expert behaviors with minimal data.
method Utilizes policy simplicity as a prior for sample-efficient imitation learning.
result Significantly higher scores achieved with limited expert demonstrations.
Paper improves communication in distributed optimization, reducing worker-to-server data exchanges.
problem Efficiency in server-to-worker communication in distributed optimization.
method MARINA-P, a novel downlink compression method using correlated compressors; M3, combining MARINA-P with uplink compression.
result MARINA-P achieves provably superior server-to-worker communication complexity with increasing number of workers.
Bayesian data sketching speeds up inference for large functional data.
problem Slow posterior computations in Bayesian varying coefficient models for large data.
method Compress functional response and predictor matrix using random linear transformation.
result Fully model-based Bayesian inference on compressed data.
IntSGD compresses SGD gradients without floats, converging as SGD.
problem Efficiently compressing stochastic gradients in distributed SGD.
method Adaptive integer compression of gradients, estimating scaling adaptively.
result IntSGD matches SGD's iteration complexity for convex and non-convex functions.
The paper defines and studies discrete p-density and compression-radius profiles of lattice knots.
problem Understanding geometric properties of lattice knots.
method Develops a framework for discrete p-density and compression-radius profiles of lattice knots, studying them on length-filtered sets and finite move-graph exploration.
result Density and compression-radius values are not monotone, illustrating distinct optimization problems.
Data-independent pruning method reduces neural network size with accuracy guarantees.
problem Limited computational and memory resources for neural networks.
method Structured pruning using coresets.
result First efficient algorithm with worst-case guarantees on compression and accuracy.
This paper compresses neural networks by permuting and quantizing weights.
problem Efficiently compressing large neural networks for resource-constrained platforms.
method Permuting and quantizing weights, connecting to rate-distortion theory, and using annealed quantization.
result Significant compression with minimal accuracy loss, e.g., 40-70% reduction in gap with uncompressed model.
Bayesian Attention Networks compress data by focusing on key training samples.
problem Lossless data compression for efficiency.
method Bayesian Attention Networks with attention factors and latent space.
result Efficient prediction using a few correlated training samples.
Study 1-bit compressive sensing with generative models, improving recovery accuracy.
problem Accurately recover sparse vectors from binary measurements with generative models.
method Analyzes noiseless and noisy 1-bit measurements with i.i.d.~Gaussian and Lipschitz continuous generative priors, proving sample complexity bounds and stability properties.
result Proves sample complexity bounds and stability properties for 1-bit compressive sensing with generative models.
Paper proposes a framework and algorithm for model compression in neural networks.
problem Training neural networks with model compression techniques suffers from accuracy loss and convergence issues.
method Holistic framework based on nonconvex optimization, using NN-BCD algorithm with closed-form iteration scheme.
result The proposed algorithm globally converges to a critical point at a rate of O(1/k).
A new deep learning framework for efficient IoT data compression and inference.
problem Limited bandwidth and power resources in IoT sensors.
method Co-designed deep learning framework that maximizes sensing goal accuracy.
result Superior performance compared to benchmark models.
New method compresses non-Gaussian distributions exponentially.
problem Efficiently representing and computing non-Gaussian probability distributions.
method Tensor-Network Fourier Methods using QTT representation.
result Exponential compression of non-Gaussian distributions.