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.
Paper uses RL to optimize bit-flipping decoding for binary codes.
A privacy-preserving method for transmitting data over a wiretap channel using generative networks.
Study introduces a benchmark suite for evaluating neural MI estimators on real-world unstructured datasets.
New exact tests detect changepoints in binary and count data, especially when normal approximations fail.
Study the tradeoff between signal distortion and human perception over finite channels.
Paper uses RNNs to design LDPC codes for binary erasure channels.
New method improves accuracy of quantized neural networks.
Deep learning optimizes polar codes for better performance.
After being trained, classifiers must often operate on data that has been corrupted by noise. In this paper, we consider the impact of such noise on the features of binary classifiers. Inspired by tools for classifier robustness, we introduce the same classification probability (SCP) to measure the resulting distortion…
The analysis of Belief Propagation and other algorithms for the {\em reconstruction problem} plays a key role in the analysis of community detection in inference on graphs, phylogenetic reconstruction in bioinformatics, and the cavity method in statistical physics. We prove a conjecture of Evans, Kenyon, Peres, and Sch…
The possibility of latency arbitrage in financial markets has led to the deployment of high-speed communication links between distant financial centers. These links are noisy and so there is a need for coding. In this paper, we develop a gametheoretic model of trading behavior where two traders compete to capture laten…
A group of transition probability functions form a Shannon's channel whereas a group of truth functions form a semantic channel. Label learning is to let semantic channels match Shannon's channels and label selection is to let Shannon's channels match semantic channels. The Channel Matching (CM) algorithm is provided f…
This paper improves multichannel speech enhancement using complex ratio masking and channel-attention.
Study predicts shear stress in compound channels using data mining and machine learning.
End-to-end learning of codes for secure BPSK communication in Gaussian wiretap channel.
This paper presents a novel approach to speaker subspace modelling based on Gaussian-Binary Restricted Boltzmann Machines (GRBM). The proposed model is based on the idea of shared factors as in the Probabilistic Linear Discriminant Analysis (PLDA). GRBM hidden layer is divided into speaker and channel factors, herein t…
Erbium-doped fiber amplifier (EDFA) is an optical amplifier/repeater device used to boost the intensity of optical signals being carried through a fiber optic communication system. A highly accurate EDFA model is important because of its crucial role in optical network management and optimization. The input channels of…
A central machine is interested in estimating the underlying structure of a sparse Gaussian Graphical Model (GGM) from datasets distributed across multiple local machines. The local machines can communicate with the central machine through a wireless multiple access channel. In this paper, we are interested in designin…
BottleNet++ compresses deep learning features for efficient mobile inference.
MeliusNet improves binary neural networks to match MobileNet-v1 accuracy.
Efficient algorithms find solutions in a rare well-connected cluster at low constraint densities.
Model detects electricity theft with high accuracy.
Study binary hypothesis testing with privacy and communication constraints.
Symmetric losses improve classifier robustness from corrupted labels.
New method for calculating HOMFLY polynomials in symmetric representations.
Study potential computational gaps in symmetric binary perceptrons using fl-RDT.
It is common wisdom that no nation is an isolated economic island. All nations participate in the global economy and are linked together through trade and finance. Here we analyze international trade network (ITN), being the network of import-export relationships between countries. We show that in each year over the an…
Sharp bounds found on expert error in binary advice aggregation.
This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.
We consider network sparsification as an -norm regularized binary optimization problem, where each unit of a neural network (e.g., weight, neuron, or channel, etc.) is attached with a stochastic binary gate, whose parameters are jointly optimized with original network parameters. The Augment-Reinforce-Merge (ARM),…
We consider active maximum a posteriori (MAP) inference problem for Hidden Markov Models (HMM), where, given an initial MAP estimate of the hidden sequence, we select to label certain states in the sequence to improve the estimation accuracy of the remaining states. We develop an analytical approach to this problem for…
Banking system crises are complex events that in a short span of time can inflict extensive damage to banks themselves and to the external economy. The crisis literature has so far identified a number of distinct effects or channels that can propagate distress contagiously both directly within the banking network itsel…
New scheme optimizes BMI through probabilistic and geometric shaping.
Paper introduces symmetric divergence link models for probability distributions.
We provide high-probability sample complexity guarantees for exact structure recovery and accurate predictive learning using noise-corrupted samples from an acyclic (tree-shaped) graphical model. The hidden variables follow a tree-structured Ising model distribution, whereas the observable variables are generated by a …
IGSD separates task-specific content channels in transformer components by comparing activation replacement with zero ablation.
This paper proposes a new approach to Transformers by integrating hierarchical associative memory with MetaFormers.
A methodology for binary classification of EEG records which correspond to different mental states is proposed. This model-free methodology is based on our theory of the -complexity of continuous functions which is extended here (see Appendix) to the case of vector functions. This extension permits us to handle mult…
This paper connects ultrametric overlap gap properties to parametric RDT for symmetric binary perceptrons.
In statistical inference problems, we wish to obtain lower bounds on the minimax risk, that is to bound the performance of any possible estimator. A standard technique to obtain risk lower bounds involves the use of Fano's inequality. In an information-theoretic setting, it is known that Fano's inequality typically doe…
A deep neural network (DNN) based power control method is proposed, which aims at solving the non-convex optimization problem of maximizing the sum rate of a multi-user interference channel. Towards this end, we first present PCNet, which is a multi-layer fully connected neural network that is specifically designed for…
Binary perceptron's instability linked to replica symmetry breaking.
Many wireless networks, including 5G NR (New Radio) and future beyond 5G cellular systems, are expected to operate on multiple frequency bands. This paper considers the band assignment (BA) problem in dual-band systems, where the basestation (BS) chooses one of the two available frequency bands (centimeter-wave and mil…
The study finds dense clusters of solutions in a simple neural network model, providing bounds for their existence.
The study sets lower bounds on MMSE for inferring sensitive features from noisy data.
Recent events such as the global financial crisis have renewed the interest in the topic of economic networks. One of the main channels of shock propagation among countries is the International Trade Network (ITN). Two important models for the ITN structure, the classical gravity model of trade (more popular among econ…
We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise when margin losses can be proper composite losses, explicitly show how to determ…
Convolutional neural networks handle rotated image symmetries without dimensionality issues.