Many users in online social networks are constantly trying to gain attention from their followers by broadcasting posts to them. These broadcasters are likely to gain greater attention if their posts can remain visible for a longer period of time among their followers' most recent feeds. Then when to post? In this pape…
On-device research index
arXiv research
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.
169,051 papers · 148 categories
Trend · papers per month
48 results for “broadcast”
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscs.LG
A new architecture improves VAE disentanglement without explicit supervision.
problem Learning disentangled representations in VAEs.
method Spatial Broadcast Decoder: tiling latent vector, concatenating coordinates, fully convolutional network.
result Improves disentangling, reconstruction accuracy, and generalization.
A new framework for parallel learning that's 10x faster.
problem Efficient parallel learning in machine learning.
method TMSN: asynchronous parallel learning using broadcast updates.
result 10 times faster than XGBoost and LightGBM on splice-site prediction.
Paper uses LSTM autoencoder for ADS-B data to detect surveillance aircraft.
problem Detecting surveillance aircraft from ADS-B flight data.
method LSTM-based sequence autoencoder for ADS-B data.
result LSTM autoencoder effectively learns features for detecting surveillance aircraft.
Study investigates FL performance over a noisy downlink, showing analog approach outperforms digital.
problem Impact of bandwidth-limited downlink on federated learning performance.
method Modelled downlink and uplink channels; proposed digital and analog downlink approaches; analyzed convergence behavior.
result Analog downlink approach provides significant improvement over digital approach, especially with biased data distribution.
New language model shows context length impacts generation quality and reasoning ability.
problem Analyzing the impact of context length and reasoning on autoregressive generation.
method Introduced synthetic hierarchical languages, used an exact k-gram ansatz, derived asymptotic predictions, and validated empirically.
result Reasoning models with limited context can generate sequences from the true language, improving exponentially over standard models.
Users in social networks whose posts stay at the top of their followers'{} feeds the longest time are more likely to be noticed. Can we design an online algorithm to help them decide when to post to stay at the top? In this paper, we address this question as a novel optimal control problem for jump stochastic different…
A new approach corrects bias in federated learning due to varying communication links.
problem Bias in federated learning due to non-uniform and time-varying communication links.
method Proposes Federated Postponed Broadcast (FedPBC) to correct bias in Federated Average (FedAvg).
result FedPBC converges to a stationary point of the global objective, overcoming bias caused by varying communication links.
The paper explores the trade-off between recommendation system performance and bandwidth usage.
problem Balancing recommendation system performance with wireless bandwidth constraints.
method Analyzes two scenarios: multi-armed bandit with context and latent structure exploitation.
result Demonstrates a tradeoff between regret and bandwidth usage, with tight bounds for some instances.
New algorithm learns uncertainty for edge devices.
problem Uncertainty handling for edge devices in critical applications.
method e-prop 1 algorithm with Broadcast Alignment and local information.
result Algorithm can learn uncertainty locally, improving decision-making.
A new method for energy-efficient file delivery in small cell networks.
problem Efficient resource management in femto-caching with time-variant statistical properties.
method Formulates a resource allocation problem as a stochastic knapsack problem and a multi-armed bandit problem, developing solutions for each.
result The proposed method maximizes the accumulated utility over the horizon, especially suitable for networks with time-variant statistical properties.
Comparison and Adaptation of Automatic Evaluation Metrics for Quality Assessment of Re-Speakingcs.CL
Re-speaking is a mechanism for obtaining high quality subtitles for use in live broadcast and other public events. Because it relies on humans performing the actual re-speaking, the task of estimating the quality of the results is non-trivial. Most organisations rely on humans to perform the actual quality assessment, …
The paper formalizes incidence tensors and their decomposition for geometric deep learning.
problem Representing structured data like graphs and simplicial complexes.
method Formalizes incidence tensors, analyzes their structure, and presents equivariant networks.
result Incidence tensors decompose into invariant subsets, leading to efficient linear map implementations.
We study large-scale kernel methods for acoustic modeling and compare to DNNs on performance metrics related to both acoustic modeling and recognition. Measuring perplexity and frame-level classification accuracy, kernel-based acoustic models are as effective as their DNN counterparts. However, on token-error-rates DNN…
Deep Neural Network (DNN) acoustic models often use discriminative sequence training that optimises an objective function that better approximates the word error rate (WER) than frame-based training. Sequence training is normally implemented using Stochastic Gradient Descent (SGD) or Hessian Free (HF) training. This pa…
Vanishing long-term gradients are a major issue in training standard recurrent neural networks (RNNs), which can be alleviated by long short-term memory (LSTM) models with memory cells. However, the extra parameters associated with the memory cells mean an LSTM layer has four times as many parameters as an RNN with the…
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 at which majority rule yields errors.
A network of spiking agents learns complex tasks using global reward signals.
problem Solving complex reinforcement learning tasks.
method A hierarchical network of GLM spiking agents, each modulating its firing policy based on local and global reward signals.
result A network of spiking agents can learn complex action representations to solve RL tasks.
FedGAN trains GANs across distributed data sources with reduced communication.
problem Training GANs across non-independent data sources with privacy and communication constraints.
method FedGAN uses local generators and discriminators synced via an intermediary, proving convergence under standard assumptions.
result FedGAN converges and performs similarly to general distributed GANs with reduced communication complexity.
Framework allows organizations to collaborate on learning tasks securely.
problem Limited collaboration due to security constraints.
method Assisted Learning framework for supervised learning tasks.
result Near-oracle learning performance achieved without revealing sensitive information.
A parallel Fortran framework for neural networks and deep learning.
problem Developing efficient parallel Fortran for neural networks and deep learning.
method Simple interface, activation functions, stochastic gradient descent, Fortran 2018 collective subroutines, parallelism with derived types and collective operations.
result Ease of use and computational performance similar to existing machine learning frameworks, suitable for production.
Linear algebra approach for parallel deep learning models.
problem Training large DNNs in distributed environments.
method Linear algebraic approach to model parallelism.
result Manual development of backward operators for gradient-based training.
The paper improves consensus-based optimization for private data sharing.
problem Privacy leakage in distributed optimization algorithms.
method Adding random noise to messages to achieve -differential privacy.
result The method converges with a bounded mean-squared error while maintaining privacy.
Cyclic Data Parallelism reduces memory usage and balances gradient communications.
problem Training large deep learning models requires efficient parallelism to scale.
method Cyclic Data Parallelism shifts micro-batches from simultaneous to sequential execution, balancing memory and gradient communications.
result Cyclic Data Parallelism reduces total memory usage and balances gradient communications.
Time delay neural networks (TDNNs) are an effective acoustic model for large vocabulary speech recognition. The strength of the model can be attributed to its ability to effectively model long temporal contexts. However, current TDNN models are relatively shallow, which limits the modelling capability. This paper propo…
Deep Convolutional Neural Networks (CNNs) are more powerful than Deep Neural Networks (DNN), as they are able to better reduce spectral variation in the input signal. This has also been confirmed experimentally, with CNNs showing improvements in word error rate (WER) between 4-12% relative compared to DNNs across a var…
Study improves efficiency of MIMO systems' sum rate estimation.
problem Maximizing sum rate in MIMO systems with PAPC constraints.
method Proposes two new low-complexity approaches: alternating optimization and machine learning.
result Demonstrates superior performance compared to existing methods.
Hessian-free training has become a popular parallel second or- der optimization technique for Deep Neural Network training. This study aims at speeding up Hessian-free training, both by means of decreasing the amount of data used for training, as well as through reduction of the number of Krylov subspace solver iterati…
I2C enables agents to learn efficient communication without redundancy.
problem Redundant broadcast communication in multi-agent cooperation.
method I2C learns a prior for agent-agent communication via causal inference and reinforcement learning.
result I2C reduces communication overhead and improves multi-agent cooperative performance.
New algorithms for collaborative learning in uncertain, decentralized environments.
problem Byzantine collaborative learning in uncertain, decentralized environments.
method Two asynchronous solutions to averaging agreement, each optimal according to some dimension.
result New algorithms achieve optimal Byzantine resilience and collaborative learning.
A new algorithm for competing agents in a two-sided market setting.
problem Decentralized competition between agents in a two-sided market with unknown valuations.
method UCB-D3 algorithm for UCB with Decentralized Dominant-arm Deletion.
result UCB-D3 is order optimal and achieves a new regret lower bound.
DBCL defends collaborative learning by sketching parameters to prevent gradient-based privacy inference attacks.
problem Privacy leaks in collaborative machine learning due to gradient-based attacks.
method Random matrix sketching applied to parameters, followed by re-generation of sketching after each iteration.
result DBCL prevents effective gradient-based privacy inference attacks without significant computational or accuracy costs.
Paper proposes MA-BERT for efficient data-driven ATM models.
problem Long training time and need for large datasets in data-driven ATM models.
method Multi-Agent Bidirectional Encoder Representations from Transformers (MA-BERT) and transfer learning framework.
result MA-BERT saves training time and achieves high performance with little data.
Random orthogonalization improves FL in massive MIMO systems without CSI.
problem Efficient model aggregation in FL with minimal channel estimation overhead.
method Combining FL with massive MIMO's channel hardening and favorable propagation, random orthogonalization reduces channel estimation overhead.
result Achieves model aggregation without CSI, significantly reducing channel estimation overhead.
Improved trajectory prediction for team sports using sparse outputs.
problem Challenging to train deep learning models for player trajectory prediction.
method Sparse trajectory prediction and constant acceleration interpolation.
result Interpolation improves performance for all tested models.
Paper develops efficient statistical estimators for distributed data.
problem Communication and privacy issues in distributed statistical inference.
method Iterative algorithms for distributed optimization, adapting to loss function similarity.
result CEASE estimators achieve statistical efficiency in finite steps.
New strategies improve multi-agent decision-making on irregular networks.
problem Maximizing group reward in multi-agent settings with heterogeneous strategies.
method Design and analysis of heterogeneous explore-exploit strategies for multi-star networks.
result Group performance improves under heterogeneous strategies compared to homogeneous strategies.
This paper proposes a semi-tied unit approach to improve efficiency in LSTM and highway networks.
problem Efficiency issues in gating mechanisms of LSTM and highway networks.
method Semi-tied units (STUs) using one shared weight matrix with extra scaling factors.
result Reduced calculation and storage costs by a factor of three for highway networks and four for LSTMs.
New algorithm reduces communication bandwidth for large-scale deep learning training.
problem Efficiently compressing gradients for ring all-reduce in large-scale clusters.
method Importance weighted pruning based on gradient and parameter size.
result Achieved significant gradient compression ratios (64X and 58.8X) on AlexNet and ResNet50.
A framework for certified unlearning in decentralized federated learning.
problem Privacy-preserving machine learning in decentralized federated learning.
method Newton-style updates to quantify and correct data influence, using Fisher information matrices for scalability.
result The proposed framework ensures that the unlearned model is difficult to distinguish from a retrained model without the deleted data.
A Deep Learning Mechanism for Efficient Information Dissemination in Vehicular Floating Contentstat.ML
Deep learning optimizes vehicular communication zones for efficient data dissemination.
problem Overdimensioning and inefficient communication in vehicular floating content.
method Deep learning is used to select optimal broadcasting areas (Anchor Zones) for efficient message dissemination.
result The proposed method achieves an accuracy of 89.7% in predicting optimal Anchor Zones, saving up to 27% of resources.
Paper studies convergence of SGD and QSGD for fitting ReLUs.
problem Finding optimal weights of shallow ReLU networks.
method Stochastic Gradient Descent (SGD) and Quantized SGD (QSGD) for distributed learning.
result QSGD achieves faster convergence with reduced communication costs.
Paper defends deep learning classifiers against channel-aware adversarial attacks.
problem Deep learning classifiers are vulnerable to adversarial attacks.
method Channel-aware adversarial attacks are presented and defended against.
result Certified defense based on randomized smoothing makes classifiers robust.
Improves data efficiency in multi-agent control tasks using model-based reinforcement learning.
problem Limited data efficiency in reinforcement learning for multi-agent tasks.
method Decentralized model-based policy optimization (DMPO) framework.
result DMPO achieves superior data efficiency and matches model-free methods using true models.
Proposes a method to improve Byzantine-robustness in compressed federated learning.
problem Byzantine-robustness in compressed federated learning.
method Gradient difference compression and stochastic average gradient algorithm (SAGA).
result The proposed method reaches a neighborhood of the optimal solution at a linear convergence rate.
The stochastic block model is one of the oldest and most ubiquitous models for studying clustering and community detection. In an exciting sequence of developments, motivated by deep but non-rigorous ideas from statistical physics, Decelle et al. conjectured a sharp threshold for when community detection is possible in…
Adversarial inference on tree models is possible with limited corruption, improving on Kesten-Stigum threshold.
problem Posterior inference on tree-structured graphical models in the presence of adversarial corruption.
method Dynamic programming via belief propagation, constrained adversarial corruption.
result Belief propagation can perform accurate inference with limited adversarial corruption.
Paper tackles energy efficiency in FL over wireless networks.
problem Energy efficient transmission and computation resource allocation for FL over wireless networks.
method Formulated as an optimization problem, iterative algorithm derived with closed-form solutions for time, bandwidth, power, and accuracy.
result Proposed algorithms reduce up to 59.5% energy consumption compared to conventional FL methods.