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 shows how to integrate quantization into neural compression models.
New adaptive SGD algorithms for federated learning over physical channels.
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…
DSF improves EEG model robustness to missing channels and noise.
Study of surfaces in space forms using Lie sphere geometry.
WaveletGAN improves GANs by homogenizing noise through multi-channel wavelet filtering.
New PAC-Bayesian bounds improve understanding of quantum machine learning generalization.
New algorithm solves Schrödinger bridge problem with mismatched channels.
Dropout-based regularization methods can be regarded as injecting random noise with pre-defined magnitude to different parts of the neural network during training. It was recently shown that Bayesian dropout procedure not only improves generalization but also leads to extremely sparse neural architectures by automatica…
This paper finds the noise threshold for learning Gaussian mixture models equals channel capacity.
The paper analyzes generalization of noisy iterative algorithms using communication theory.
Inspired by recent advances in deep learning, we propose a novel iterative BP-CNN architecture for channel decoding under correlated noise. This architecture concatenates a trained convolutional neural network (CNN) with a standard belief-propagation (BP) decoder. The standard BP decoder is used to estimate the coded b…
Paper proposes integrating wavelet transform, channel attention, and LSTM for better stock price prediction.
The idea of end-to-end learning of communications systems through neural network -based autoencoders has the shortcoming that it requires a differentiable channel model. We present in this paper a novel learning algorithm which alleviates this problem. The algorithm iterates between supervised training of the receiver …
Paper tackles federated linear bandit learning with AirComp for noisy channels.
Interpolating label noise makes models vulnerable to adversarial attacks.
This paper shows how differential privacy can be achieved naturally in federated learning over fading channels without artificial noise.
A privacy-preserving method for transmitting data over a wiretap channel using generative networks.
Channel modeling is a critical topic when considering designing, learning, or evaluating the performance of any communications system. Most prior work in designing or learning new modulation schemes has focused on using highly simplified analytic channel models such as additive white Gaussian noise (AWGN), Rayleigh fad…
Majority bit estimation in noisy random recursive DAGs.
Single-channel signal separation and deconvolution aims to separate and deconvolve individual sources from a single-channel mixture and is a challenging problem in which no prior knowledge of the mixing filters is available. Both individual sources and mixing filters need to be estimated. In addition, a mixture may con…
We propose a novel receiver for orthogonal frequency division multiplexing (OFDM) transmissions in impulsive noise environments. Impulsive noise arises in many modern wireless and wireline communication systems, such as Wi-Fi and powerline communications, due to uncoordinated interference that is much stronger than the…
PruneNet efficiently prunes channels in deep networks, improving accuracy and performance.
We present a new method for the separation of superimposed, independent, auto-correlated components from noisy multi-channel measurement. The presented method simultaneously reconstructs and separates the components, taking all channels into account and thereby increases the effective signal-to-noise ratio considerably…
Paper introduces REED for noncoherent OTA-FL, reducing latency without phase alignment.
Paper addresses FL over MAC with DP constraints, proposing a novel consensus scheme.
Adding noise controls capacity of function compositions.
The emergence of various intelligent mobile applications demands the deployment of powerful deep learning models at resource-constrained mobile devices. The device-edge co-inference framework provides a promising solution by splitting a neural network at a mobile device and an edge computing server. In order to balance…
A nonlinear channel estimator using complex Least Square Support Vector Machines (LS-SVM) is proposed for pilot-aided OFDM system and applied to Long Term Evolution (LTE) downlink under high mobility conditions. The estimation algorithm makes use of the reference signals to estimate the total frequency response of the …
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…
Channel Pruning, widely used for accelerating Convolutional Neural Networks, is an NP-hard problem due to the inter-layer dependency of channel redundancy. Existing methods generally ignored the above dependency for computation simplicity. To solve the problem, under the Bayesian framework, we here propose a layer-wise…
Efficient deep learning for wireless source identification using test SNR estimates.
New algorithms for hypothesis testing in high-dimensional data are shown to be effective under various noisy conditions.
Deep learning (DL) based autoencoder has shown great potential to significantly enhance the physical layer performance. In this paper, we present a DL based autoencoder for interference channel. Based on a characterization of a k-user Gaussian interference channel, where the interferences are classified as different le…
PCA++ improves robustness to background noise in contrastive learning.
Improved federated learning over-the-air reduces noise impact.
New scheme optimizes BMI through probabilistic and geometric shaping.
Paper defends deep learning classifiers against channel-aware adversarial attacks.
The paper improves alignment methods for deep neural networks using geometric and spectral analysis.
The paper examines conditions for linearity in a conditional mean estimator under vector Poisson noise.
The U-net is a deep-learning network model that has been used to solve a number of inverse problems. In this work, the concatenation of two-element U-nets, termed the W-net, operating in k-space (K) and image (I) domains, were evaluated for multi-channel magnetic resonance (MR) image reconstruction. The two element net…
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…
New communication standards need to deal with machine-to-machine communications, in which users may start or stop transmitting at any time in an asynchronous manner. Thus, the number of users is an unknown and time-varying parameter that needs to be accurately estimated in order to properly recover the symbols transmit…
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…
Theory explains generalization in deep learning, reducing memorization and improving performance.
For reliable transmission across a noisy communication channel, classical results from information theory show that it is asymptotically optimal to separate out the source and channel coding processes. However, this decomposition can fall short in the finite bit-length regime, as it requires non-trivial tuning of hand-…
A-MMSE uses attention to learn efficient OFDM channel estimation.
Quaternion neural networks improve distant speech recognition.