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.
IDF++ improves integer discrete flows for lossless compression.
Lossless compression methods shorten the expected representation size of data without loss of information, using a statistical model. Flow-based models are attractive in this setting because they admit exact likelihood optimization, which is equivalent to minimizing the expected number of bits per message. However, con…
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…
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.
Paper extends port-Hamiltonian model to include internal energy for compressible and incompressible flow.
Computational Fluid Dynamics (CFD) is a hugely important subject with applications in almost every engineering field, however, fluid simulations are extremely computationally and memory demanding. Towards this end, we present Lat-Net, a method for compressing both the computation time and memory usage of Lattice Boltzm…
We solve image inverse problems using a flow-based noise model.
Discrete Flow Maps bypass sequential prediction limits for parallel text generation.
We study the problem of inviscid slightly compressible fluids in a bounded domain. We find a unique solution to the initial-boundary value problem and show that it is near the analogous solution for an incompressible fluid provided the initial conditions for the two problems are close. In particular, the divergence of …
SHVC improves image compression with fewer parameters.
New method compresses facial videos using GANs and latent space optimization.
New method reduces Bayesian inference time by optimizing Hamiltonian flows.
DiffC compresses images by diffusing Gaussian noise, outperforming state-of-the-art methods.
Paper develops a new fluid flow model with energy exchange through boundaries.
We consider maps between Riemannian manifolds in which the map is a stationary point of the nonlinear Hodge energy. The variational equations of this functional form a quasilinear, nondiagonal, nonuniformly elliptic system which models certain kinds of compressible flow. Conditions are found under which singular sets o…
Model compresses event-like contexts using gated surprise signals.
We extend quantization-aware training to extreme model compression.
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…
Intrusion Detection System (IDS) is one of the most effective solutions for providing primary security services. IDSs are generally working based on attack signatures or by detecting anomalies. In this paper, we have presented AutoIDS, a novel yet efficient solution for IDS, based on a semi-supervised machine learning …
We study the flow of information and the evolution of internal representations during deep neural network (DNN) training, aiming to demystify the compression aspect of the information bottleneck theory. The theory suggests that DNN training comprises a rapid fitting phase followed by a slower compression phase, in whic…
CCVFM uses coreset to improve generative models by refining residual flows.
Image compression techniques reveal network structure for shipping box optimization.
Preconditioned NFs speed up sampling from complex posterior distributions in inverse problems.
Stable long-term predictions for fluid flows using neural networks.
Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on learning are largely unexplored. Further, the Gaussian prior assumptions in model…
We present a deep generative model, named Monge-Ampère flow, which builds on continuous-time gradient flow arising from the Monge-Ampère equation in optimal transport theory. The generative map from the latent space to the data space follows a dynamical system, where a learnable potential function guides a compressible…
Over the past few years, we developed a mathematically rigorous method to study the dynamical processes associated to nonlinear Forchheimer flows for slightly compressible fluids. We have proved the existence of a geometric transformation which relates constant mean curvature surfaces and time-invariant pressure distri…
Given the superposition of a low-rank matrix plus the product of a known fat compression matrix times a sparse matrix, the goal of this paper is to establish deterministic conditions under which exact recovery of the low-rank and sparse components becomes possible. This fundamental identifiability issue arises with tra…
CPFM integrates dimensionality reduction and reconstruction with flow networks.
Image compression is an essential approach for decreasing the size in bytes of the image without deteriorating the quality of it. Typically, classic algorithms are used but recently deep-learning has been successfully applied. In this work, is presented a deep super-resolution work-flow for image compression that maps …
Analysis of Vlasov plasma dynamics using matched pair Lie-Poisson formulation.
Bayesian methods have been successfully applied to sparsify weights of neural networks and to remove structure units from the networks, e. g. neurons. We apply and further develop this approach for gated recurrent architectures. Specifically, in addition to sparsification of individual weights and neurons, we propose t…
We propose a new method of discovering causal relationships in temporal data based on the notion of causal compression. To this end, we adopt the Pearlian graph setting and the directed information as an information theoretic tool for quantifying causality. We introduce chain rule for directed information and use it to…
Bayesian method improves dictionary learning for complex problems.
We present a new algorithm for video coding, learned end-to-end for the low-latency mode. In this setting, our approach outperforms all existing video codecs across nearly the entire bitrate range. To our knowledge, this is the first ML-based method to do so. We evaluate our approach on standard video compression test …
Paper proves CFlows can approximate any diffeomorphism and applies it in Bayesian optimization.
Flexible VAEs using FIFs improve model likelihood on image datasets.
Deep neural networks have dramatically achieved great success on a variety of challenging tasks. However, most successful DNNs have an extremely complex structure, leading to extensive research on model compression.As a significant area of progress in model compression, traditional gradual pruning approaches involve an…
W-Flow generates images in one step, faster and better than multi-step methods.
Flexible framework compresses models using LC algorithm.
Reduces multiclass and regression compression schemes to binary ones.
Proposes a link between randomness and compression in deep learning.
In this work, we analyze the flow filtration process of slightly compressible fluids in porous media containing man made fractures with complex geometries. We model the coupled fracture-porous media system where the linear Darcy flow is considered in porous media and the nonlinear Forchheimer equation is used inside th…
Jointly estimates flow fields and particle properties from Lagrangian data.
Paper introduces a new adaptive gradient method with gradient compression for distributed training.
Galen algorithm compresses neural networks for specific hardware with reduced latency.
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…
Neural NCD reveals LLMs don't compress well for classification.