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.
BestChanID identifies the channel with maximal capacity using training sequences.
While the channel capacity reflects a theoretical upper bound on the achievable information transmission rate in the limit of infinitely many bits, it does not characterise the information transfer of a given encoding routine with finitely many bits. In this note, we characterise the quality of a code (i. e. a given en…
Modeling alignment as resource-limited cognitive processes, researchers derive performance bounds.
This paper finds the noise threshold for learning Gaussian mixture models equals channel capacity.
Truncated Singular Value Decomposition (SVD) calculates the closest rank- approximation of a given input matrix. Selecting the appropriate rank defines a critical model order choice in most applications of SVD. To obtain a principled cut-off criterion for the spectrum, we convert the underlying optimization prob…
Sparse superposition codes were recently introduced by Barron and Joseph for reliable communication over the AWGN channel at rates approaching the channel capacity. The codebook is defined in terms of a Gaussian design matrix, and codewords are sparse linear combinations of columns of the matrix. In this paper, we prop…
This work improves communication efficiency in federated learning over wireless networks by optimizing energy consumption.
Given a classical channel---a stochastic map from inputs to outputs---the input can often be transformed to an intermediate variable that is informationally smaller than the input. The new channel accurately simulates the original but at a smaller transmission rate. Here, we examine this procedure when the intermediate…
We propose a joint source and channel coding (JSCC) technique for wireless image transmission that does not rely on explicit codes for either compression or error correction; instead, it directly maps the image pixel values to the complex-valued channel input symbols. We parameterize the encoder and decoder functions b…
The choice of constellations largely affects the performance of communication systems. When designing constellations, both the locations and probability of occurrence of the points can be optimized. These approaches are referred to as geometric and probabilistic shaping, respectively. Usually, the geometry of the const…
In this paper, we model Density Evolution (DE) using Recurrent Neural Networks (RNNs) with the aim of designing capacity-approaching Irregular Low-Density Parity-Check (LDPC) codes for binary erasure channels. In particular, we present a method for determining the coefficients of the degree distributions, characterizin…
New PAC-Bayesian bounds improve understanding of quantum machine learning generalization.
Recent progress in deep convolutional neural networks (CNNs) have enabled a simple paradigm of architecture design: larger models typically achieve better accuracy. Due to this, in modern CNN architectures, it becomes more important to design models that generalize well under certain resource constraints, e.g. the numb…
Following the recent work on capacity allocation, we formulate the conjecture that the shattering problem in deep neural networks can only be avoided if the capacity propagation through layers has a non-degenerate continuous limit when the number of layers tends to infinity. This allows us to study a number of commonly…
We consider wireless transmission of images in the presence of channel output feedback. From a Shannon theoretic perspective feedback does not improve the asymptotic end-to-end performance, and separate source coding followed by capacity-achieving channel coding, which ignores the feedback signal, achieves the optimal …
Introduces geometric formulation of EM algorithm for robust inference and various applications.
In this paper, we present NESTA, a specialized Neural engine that significantly accelerates the computation of convolution layers in a deep convolutional neural network, while reducing the computational energy. NESTA reformats Convolutions into batches and uses a hierarchy of Hamming Weight Compressors to …
The statistical complexity of quantum circuits is studied using Rademacher complexity.
Auto-Compressing Subset Pruning reduces model size for faster inference.
Many recent works have discussed the propensity, or lack thereof, for emergent languages to exhibit properties of natural languages. A favorite in the literature is learning compositionality. We note that most of those works have focused on communicative bandwidth as being of primary importance. While important, it is …
Rényi divergence is related to Rényi entropy much like Kullback-Leibler divergence is related to Shannon's entropy, and comes up in many settings. It was introduced by Rényi as a measure of information that satisfies almost the same axioms as Kullback-Leibler divergence, and depends on a parameter that is called its or…
Study on CNNs' learning rates and approximation capacities.
Mix2FLD improves FL accuracy with FD, reducing convergence time.
Graph neural networks optimize radio resource management policies for wireless networks.
Paper addresses FL over MAC with DP constraints, proposing a novel consensus scheme.
We present an iterative Markov chainMonte Carlo algorithm for computingreference priors and minimax risk forgeneral parametric families. Ourapproach uses MCMC techniques based onthe Blahut-Arimoto algorithm forcomputing channel capacity ininformation theory. We give astatistical analysis of the algorithm,bounding the n…
In a physical neural system, where storage and processing are intimately intertwined, the rules for adjusting the synaptic weights can only depend on variables that are available locally, such as the activity of the pre- and post-synaptic neurons, resulting in local learning rules. A systematic framework for studying t…
Millimeter Wave (MmWave) communication is one of the key technology of the fifth generation (5G) wireless systems to achieve the expected 1000x data rate. With large bandwidth at mmWave band, the link capacity between users and base stations (BS) can be much higher compared to sub-6GHz wireless systems. Meanwhile, due …
FEDS distills LIC model knowledge into a lightweight student for efficient compression.
SAMformer improves transformer performance in time series forecasting.
In this paper, we study the randomized distributed coordinate descent algorithm with quantized updates. In the literature, the iteration complexity of the randomized distributed coordinate descent algorithm has been characterized under the assumption that machines can exchange updates with an infinite precision. We con…
Study on statistical estimation over Gaussian MAC, comparing analog and digital schemes.
Binary Neural Networks (BNNs) are neural networks which use binary weights and activations instead of the typical 32-bit floating point values. They have reduced model sizes and allow for efficient inference on mobile or embedded devices with limited power and computational resources. However, the binarization of weigh…
We introduce a methodology for efficiently computing a lower bound to empowerment, allowing it to be used as an unsupervised cost function for policy learning in real-time control. Empowerment, being the channel capacity between actions and states, maximises the influence of an agent on its near future. It has been sho…
We present a method that trains large capacity neural networks with significantly improved accuracy and lower dynamic computational cost. We achieve this by gating the deep-learning architecture on a fine-grained-level. Individual convolutional maps are turned on/off conditionally on features in the network. To achieve…
Exploration is a difficult challenge in reinforcement learning and is of prime importance in sparse reward environments. However, many of the state of the art deep reinforcement learning algorithms, that rely on epsilon-greedy, fail on these environments. In such cases, empowerment can serve as an intrinsic reward sign…
Shared workspace improves neural module coordination in deep learning.
Constrained sequence codes have been widely used in modern communication and data storage systems. Sequences encoded with constrained sequence codes satisfy constraints imposed by the physical channel, hence enabling efficient and reliable transmission of coded symbols. Traditional encoding and decoding of constrained …
For high data rate wireless communication systems, developing an efficient channel estimation approach is extremely vital for channel detection and signal recovery. With the trend of high-mobility wireless communications between vehicles and vehicles-to-infrastructure (V2I), V2I communications pose additional challenge…
Attention mechanism is a hot spot in deep learning field. Using channel attention model is an effective method for improving the performance of the convolutional neural network. Squeeze-and-Excitation block takes advantage of the channel dependence, selectively emphasizing the important channels and compressing the rel…
CN normalizes channels for better time series model performance.
Proposes dynamic channel pruning during neural network training.
A new DVAE architecture improves channel estimation by incorporating temporal correlations.
Generative diffusion models improve channel sampling from limited data.
A privacy-preserving method for transmitting data over a wiretap channel using generative networks.
New adaptive SGD algorithms for federated learning over physical channels.
We present a definition of discrete channel surfaces in Lie sphere geometry, which reflects several properties for smooth channel surfaces. Various sets of data, defined at vertices, on edges or on faces, are associated with a discrete channel surface that may be used to reconstruct the underlying particular discrete L…
VAE leverages MMSE channel estimation with data-driven modeling.