Paper studies distributed learning with limited communication bits, achieving optimal error exponents.
problem Distributed hypothesis testing with constant communication bits.
method Geometric approach in distribution spaces, encoding empirical distributions to transmission bits.
result Optimal achievable error exponents and coding schemes for various communication constraints.
The paper proposes a nonparametric test for incomplete samples quantized to B bits.
problem Statistical inference with lossy or incomplete samples.
method Nonparametric testing procedure based on B-bit quantized samples.
result The proposed test achieves the classical minimax rate of testing for spline models when B exceeds a threshold.
We optimize distributed learning algorithms to maintain linear convergence with limited communication.
problem Limited communication time affects the convergence of distributed learning algorithms.
method We design quantizers to compress algorithm information while preserving linear convergence and characterize communication time.
result We show how to co-design machine learning and communication protocols for optimal performance.
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…
The one-bit quantization is implemented by one single comparator that operates at low power and a high rate. Hence one-bit compressive sensing (1bit-CS) becomes attractive in signal processing. When measurements are corrupted by noise during signal acquisition and transmission, 1bit-CS is usually modeled as minimizing …
End-to-end deep learning boosts IM/DD fiber communication over dispersive channels.
problem Improving data transmission over dispersive IM/DD channels with memory.
method Bidirectional recurrent neural network (BRNN) for end-to-end deep learning of the communication system.
result End-to-end SBRNN achieves significant bit-error-rate reduction compared to FFNNs.
Diffusion models improve image compression at low bit-rates.
problem Efficiently compressing images at very low bit-rates.
method Encoding into an embedding, using diffusion models to refine the embedding iteratively.
result Realistic reconstructions can be generated at extremely low bit-rates.
Quantized-TinyLLaVA reduces communication costs in split learning for multimodal models.
problem High communication costs in split learning for multimodal models.
method Integrates a compression module that quantizes intermediate features into discrete representations before transmission.
result Achieves an approximate 87.5% reduction in communication overhead with 2-bit quantization.
Deep learning improves decoding of constrained sequence codes, reducing errors and increasing throughput.
problem Errors during transmission of constrained sequence codes.
method Deep learning, specifically MLP and CNN networks.
result Achieved low bit error rates close to MAP decoding and improved system throughput.
Paper introduces adversarial lossy compression for video artifacts reduction.
problem Unpleasant reconstruction artifacts in standard video coding schemes at low bit-rates.
method Adversarial lossy video compression model minimizing an adversarial distortion objective.
result Reduction of perceptual artifacts and detail reconstruction under extreme compression.
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…
Jointly learns encoding and decoding for noisy channels.
problem Asymptotic optimality of source and channel separation in finite bit-length regimes.
method Discrete variational autoencoder model with noise simulation.
result Jointly learned codes are competitive and learn robust representations.
This paper considers a cross-layer adaptive modulation system that is modeled as a Markov decision process (MDP). We study how to utilize the monotonicity of the optimal transmission policy to relieve the computational complexity of dynamic programming (DP). In this system, a scheduler controls the bit rate of the m-qu…
Two parties estimate cross-correlation matrix from i.i.d. samples, achieving near-optimal variance.
problem Estimating cross-correlation matrix between two parts of a random vector.
method Constructive unbiased estimators for jointly and vector Gaussian cases, leveraging i.i.d. samples and bit transmission.
result Achieves variance of (1−ρ2)/(2kln2) for jointly Gaussian scalar random variables, and uniformly better for vector Gaussian case. Adversarial machine learning hides 5G communications from eavesdroppers.
problem Hiding 5G communications from eavesdroppers using DL classifiers.
method Craft adversarial perturbations to fool DL classifiers.
result Adversarial perturbations can hide 5G communications with high probability.
RFML systems are vulnerable to adversarial attacks, especially in OTA transmissions.
problem Vulnerability of RFML systems to adversarial machine learning attacks.
method Differentiated adversarial threats, developed methodology for evaluating vulnerabilities, used Fast Gradient Sign Method.
result RFML systems are vulnerable to adversarial examples, even in OTA attacks.
New MIMO constellation design for noncoherent communications reduces hardware complexity.
problem Designing efficient MIMO constellations for noncoherent communications over fading channels.
method Geodesic curves of the Grassmann manifold for structured constellation design.
result Achieves comparable error performance to unstructured designs with reduced hardware complexity.
New method learns transmission matrices from input-output data.
problem Recovering transmission matrices from input-output data in random media.
method Statistical mechanical formulation and pseudolikelihood maximization.
result Inference protocols can learn transmission couplings.
New techniques improve 16-bit training accuracy without 32-bit units.
problem Training deep learning models with only 16-bit floating-point units.
method Studied BFloat16 units and applied stochastic rounding and Kahan summation techniques.
result Up to 7% absolute validation accuracy gain in 16-bit-FPU training.
This paper uses deep reinforcement learning to automate electric transmission voltage control.
problem Automating voltage control in electric transmission systems.
method Deep reinforcement learning (DRL) applied to voltage control, with a novel DQN modification.
result DRL can automate voltage control at scale, but more research is needed.
Bayesian Bits unifies quantization and pruning through gradient optimization.
problem Joint mixed precision quantization and pruning for efficient neural networks.
method Gradient-based optimization with a novel bit width decomposition and learnable stochastic gates.
result Bayesian Bits achieves better accuracy vs. efficiency trade-off compared to static bit width networks.
New method shows cultural transmission improves language compositionality.
problem How cultural transmission affects language emergence and compositionality.
method Introduced cultural evolutionary dynamics into language emergence by periodically replacing agents in a population.
result Languages emerge with better compositional generalization due to implicit cultural transmission.
The sum-product or belief propagation (BP) algorithm is a widely-used message-passing algorithm for computing marginal distributions in graphical models with discrete variables. At the core of the BP message updates, when applied to a graphical model with pairwise interactions, lies a matrix-vector product with complex…
Low-bit training framework reduces energy consumption in CNNs.
problem Reducing energy consumption in convolutional neural networks.
method Low-bit training framework using MLS tensor format with dynamic quantization.
result Achieves superior trade-off between accuracy and bit-width.
Researchers use statistical methods to infer transmission matrices in complex media.
problem Comprehending and exploiting photon scattering through disordered media.
method Pseudolikelihood decimation to learn the coupling matrix via random sampling.
result Transmission matrices can be inferred and used like normal optical elements.
New framework analyzes belief evolution in social networks.
problem Analyzing belief evolution in social networks.
method Proposes a new theoretical framework using Markov chain theory for horizontal and vertical transmission.
result Homophily-based networks do not converge to a single set of beliefs.
Bit-Swap improves lossless compression for hierarchical latent variable models.
problem Efficient lossless compression for latent variable models with hierarchical structure.
method Generalizes bits-back coding to hierarchical latent variable models with Markov chain structure.
result Achieves superior lossless compression rates for hierarchical latent variable models.
BottleNet++ compresses deep learning features for efficient mobile inference.
problem Balancing computation and communication in mobile devices with deep learning models.
method End-to-end architecture with encoder, non-trainable channel layer, and decoder.
result Achieves high compression ratio and bandwidth reduction with minimal accuracy loss.
Optimizes data transmission timing to minimize user information age.
problem Minimizing long-term average age of information in multi-user networks.
method Reinforcement learning applied to scheduling decisions without channel state information.
result RL approach effectively reduces AoI compared to traditional ARQ and HARQ.
Optimizes QoS in FSO links over South Africa using ensemble learning.
problem Impact of weather on QoS in FSO links.
method Ensemble learning models (Random Forest, ADaBoost Regression, Stacking Regression, Gradient Boost Regression, Multilayer Neural Network) applied to meteorological data.
result Significant enhancement in QoS with RMSE and R-squared values of 0.0032 and 0.9906 respectively at George.
Paper improves DNN accelerator robustness against bit errors with energy savings.
problem Bit errors in quantized DNN weights reduce energy efficiency.
method Combines robust fixed-point quantization, weight clipping, and random bit error training.
result Significantly improves robustness against random bit errors with high energy savings.
This paper considers a transmission control problem in network-coded two-way relay channels (NC-TWRC), where the relay buffers random symbol arrivals from two users, and the channels are assumed to be fading. The problem is modeled by a discounted infinite horizon Markov decision process (MDP). The objective is to find…
Training deep neural networks with 8-bit floating point numbers is now possible and more efficient.
problem Challenges in training DNNs with reduced precision, especially for gradient computations.
method Introduction of chunk-based accumulation and floating point stochastic rounding to reduce arithmetic precision to 16 bits.
result Successful training of DNNs using 8-bit floating point numbers, maintaining accuracy on various models and datasets.
This work interprets GELU and related activations via a first-order loss function.
problem Understanding and optimizing activation functions in neural networks.
method Complementary interpretation using the Gaussian first-order loss function.
result Calibrated or learned uniform-threshold gates are competitive and often outperform GELU, ReLU, and SiLU/Swish.
A deep learning approach for efficient power control in wireless video transmissions.
problem Optimizing power control for real-time wireless video transmissions with quality constraints.
method Proposes a learning-based approach using a deep neural network to solve the non-convex power control problem.
result The deep neural network can quickly provide optimal power levels for given channel conditions.
Bit-slice sparsity improves ReRAM-based DNN acceleration.
problem Limited ADC power and area constraints in ReRAM-based DNN accelerators.
method Proposed bit-slice L1 algorithm to induce sparsity during training.
result 2x sparsity improvement compared to previous methods.
Anomaly detection identifies unusual malaria transmission patterns in Ghana.
problem Identifying atypical malaria transmission patterns in Ghana's spatiotemporal surveillance data.
method Consensus-based anomaly detection framework applied to monthly malaria surveillance data.
result High-burden areas are not necessarily those with the most frequent anomalous transmission.
In this note, we present some interesting observations on the Schiffer's conjecture, interior transmission eigenvalue problem and their connections to singular and nonsingular invisibility cloaking problems of acoustic waves.
Transmission imaging, as an important imaging technique widely used in astronomy, medical diagnosis, and biology science, has been shown in [49] quite different from reflection imaging used in our everyday life. Understanding the structures of images (the prior information) is important for designing, testing, and choo…
Graph neural network optimizes energy-efficient precoding for massive MIMO systems.
problem Energy bottleneck in massive MIMO systems due to high DAC complexity and power consumption.
method Proposes a graph neural network to directly output precoded quantized vectors from channel matrix and transmit symbols.
result Significant increase in achievable sum rate with reduced DAC power consumption.
Traders and investors involved in an option contract having the underlying stock in range bound are likely to lose their initial investment. Timing in buying an option contract is of capital importance. In a recent article [1] the hypothesis of range bound market is used in conjunction to Black-Scholes equation to find…
DeepJSCC-f uses feedback to improve image transmission quality.
problem Improve image transmission quality in feedback channels.
method Autoencoder-based joint source-channel coding (DeepJSCC-f) exploiting feedback.
result Improves reconstruction quality for fixed-length or variable-length transmission.
Estimating mean from one-bit samples of symmetric log-concave distributions.
problem Estimating the mean of a symmetric log-concave distribution with limited one-bit measurements.
method Analyzes mean squared error in three settings: centralized, adaptive, and distributed, with and without quantization.
result One round of adaptivity is sufficient to achieve optimal mean-square error in the adaptive setting.
Majority bit estimation in noisy random recursive DAGs.
problem Estimating the majority bit in a noisy random recursive DAG.
method Majority rule among nodes, with bit flipping and noisy channel.
result Identification of the threshold for p at which majority rule yields errors. Paper proposes a CNN-based method for estimating intra frame bits and quality.
problem Efficient video delivery and bit allocation in video coding.
method Deep learning approach using CNNs trained on original frames and encoded distortions.
result Accurate estimation of intra frame bits and quality for better bit allocation.
Mathematical framework for cooperative communication explains belief transmission.
problem Lack of understanding why cooperation enables effective belief transmission.
method Connection to optimal transport theory, deriving prior models, statistical interpretations, proofs of robustness and instability.
result Cooperative communication provably enables effective, robust belief transmission.
Improves matrix multiplication throughput for asymmetric bit-width operands.
problem Matrix multiplications between asymmetric bit-width operands, especially 8- and 4-bit, are not efficiently handled by existing SIMD instructions.
method Proposes a new SIMD matrix multiplication instruction that uses mixed precision on inputs (8- and 4-bit) and accumulates into 16-bit output, improving throughput.
result Offers 2x improvement in throughput compared to existing symmetric-operand-size instructions, with negligible overflow.
Bit threads prove holographic monogamy of mutual information.
problem Proving the monogamy of mutual information in holographic entanglement.
method Using bit threads and multicommodity flow adapted from network theory, combined with convex optimization tools.
result Proved the monogamy of mutual information property of holographic entanglement entropies.