arXiv research

Paper proves integrability and entropy compactness for Kähler potentials with uniform log-log threshold.

New stability thresholds detect K-stability in Fano manifolds.

The goal of this paper is to explore the basic Approximate Bayesian Computation (ABC) algorithm via the lens of information theory. ABC is a widely used algorithm in cases where the likelihood of the data is hard to work with or intractable, but one can simulate from it. We use relative entropy ideas to analyze the beh…

Study on the limits of learning HMM parameters under various conditions.

Using a recently developed method of noise level estimation that makes use of properties of the coarse grained-entropy we have analyzed the noise level for the Dow Jones index and a few stocks from the New York Stock Exchange. We have found that the noise level ranges from 40 to 80 percent of the signal variance. The c…

Paper improves deep point cloud compression techniques.

Every production-recycling iteration accumulates an inevitable proportion of its matter-energy in the environment, lest the production process itself would be a system in perpetual motion, violating the second law of Thermodynamics. Such high-entropy matter depletes finite stocks of ecosystem services provided by the e…

Understanding the inductive bias of neural networks is critical to explaining their ability to generalise. Here, for one of the simplest neural networks -- a single-layer perceptron with n input neurons, one output neuron, and no threshold bias term -- we prove that upon random initialisation of weights, the a priori p…

EAST aligns neural network classifiers with user-defined evaluation metrics.

MESMOC optimizes constrained multi-objective problems efficiently.

Proves uniform K-stability is open in Kähler cone.

Time changes of noise level at Warsaw Stock Market are analyzed using a recently developed method basing on properties of the coarse grained entropy. The condition of the minimal noise level is used to build an efficient portfolio. Our noise level approach seems to be a much better tool for risk estimations than standa…

The scientific method relies on the iterated processes of inference and inquiry. The inference phase consists of selecting the most probable models based on the available data; whereas the inquiry phase consists of using what is known about the models to select the most relevant experiment. Optimizing inquiry involves …

Entropy-based decoding improves DLM sampling efficiency.

Entropy regularization improves sparse model discovery in federated learning.

We address online combinatorial optimization when the player has a prior over the adversary's sequence of losses. In this framework, Russo and Van Roy proposed an information-theoretic analysis of Thompson Sampling based on the information ratio, resulting in optimal worst-case regret bounds. In this paper we introduce…

System classifies lung CT scans into normal or COVID-19 using machine learning.

We study the quantification of uncertainty of Convolutional Neural Networks (CNNs) based on gradient metrics. Unlike the classical softmax entropy, such metrics gather information from all layers of the CNN. We show for the EMNIST digits data set that for several such metrics we achieve the same meta classification acc…

New method reduces GP bandit complexity while maintaining good performance.

New feature selection method DRPT reduces genomic datasets by removing irrelevant features and detecting correlations.

This paper establishes minimax rates for online regression with arbitrary classes of functions and general losses. We show that below a certain threshold for the complexity of the function class, the minimax rates depend on both the curvature of the loss function and the sequential complexities of the class. Above this…

The paper accelerates LLM inference by adding early exit heads trained in a self-supervised manner.

Clustering explores meaningful patterns in the non-labeled data sets. Cluster Ensemble Selection (CES) is a new approach, which can combine individual clustering results for increasing the performance of the final results. Although CES can achieve better final results in comparison with individual clustering algorithms…

This paper extends neural collapse to imbalanced data under cross-entropy loss.

New framework assesses LM uncertainty without thresholding.

Unified geometric flows improve deep learning efficiency and simplify neural network topologies.

--- the companies populating a Stock market, along with their connections, can be effectively modeled through a directed network, where the nodes represent the companies, and the links indicate the ownership. This paper deals with this theme and discusses the concentration of a market. A cross-shareholding matrix is co…

Study potential computational gaps in symmetric binary perceptrons using fl-RDT.

This paper extends financial theory to measure learnable market structure under computational constraints.

An algorithmically hard phase was described in a range of inference problems: even if the signal can be reconstructed with a small error from an information theoretic point of view, known algorithms fail unless the noise-to-signal ratio is sufficiently small. This hard phase is typically understood as a metastable bran…

New algorithm enhances generative modeling for bounded domains.

ML models predict extreme events in the Hénon map with accuracy scaling with system parameters.

Adaptive Nucleus Truncation Improves Long-Form Reasoning

A single algebraic identity unifies information-theoretic variational results.

Recently the deep learning techniques have achieved success in multi-label classification due to its automatic representation learning ability and the end-to-end learning framework. Existing deep neural networks in multi-label classification can be divided into two kinds: binary relevance neural network (BRNN) and thre…

Iterative thresholding algorithms seek to optimize a differentiable objective function over a sparsity or rank constraint by alternating between gradient steps that reduce the objective, and thresholding steps that enforce the constraint. This work examines the choice of the thresholding operator, and asks whether it i…

Developed a new thresholding method that connects soft and hard thresholding.

New method finds rare dense clusters in asymmetric binary perceptrons, resolving algorithmic hardness.

Proposes mutual information for regression without prior knowledge.

This paper connects ultrametric overlap gap properties to parametric RDT for symmetric binary perceptrons.

New algorithm for reinforcement learning in uncertain environments with unknown thresholds.

A new SSL method uses instance-dependent thresholds to improve accuracy.

Study stability thresholds of big line bundles, proving bounds and generalizing results.

Adaptive algorithm for outlier detection by balancing arm exploration and threshold estimation.

In this paper we studied about the wavelet identification of the thresholds and time delay for more general case without the constraint that the time delay is smaller than the order of the model. Here we composed an empirical wavelet from the SETAR (Self-Exciting Threshold Autoregressive) model and identified the thres…

Study analyzes Airbnb lead-time distributions for Nights Booked and Gross Booking Value, finding divergent shapes and tail behavior.

The paper develops a theory for speculative decoding acceptance criteria.

The study shows that the visible range from a point on harmonic manifolds follows an exponential distribution.