arXiv research

FedLog reduces communication in federated learning by sharing data summaries.

New protocols implement logical gates on encoded qubits with minimal overhead.

Deep learning reduces training overhead in massive MIMO systems.

We consider the problem of learning a binary classifier from $n$ different data sources, among which at most an $η$ fraction are adversarial. The overhead is defined as the ratio between the sample complexity of learning in this setting and that of learning the same hypothesis class on a single data distribution. We pr…

We study the collaborative PAC learning problem recently proposed in Blum et al.~\cite{BHPQ17}, in which we have $k$ players and they want to learn a target function collaboratively, such that the learned function approximates the target function well on all players' distributions simultaneously. The quality of the col…

New method reduces parameter overhead for Bayesian neural networks.

SRG improves optimization efficiency with reduced memory and computation overhead.

Federated LIDAR aided beam selection reduces mmWave beam search overhead.

New method estimates uncertainty without sampling for neural networks.

The computation of convolution layers in deep neural networks typically rely on high performance routines that trade space for time by using additional memory (either for packing purposes or required as part of the algorithm) to improve performance. The problems with such an approach are two-fold. First, these routines…

Turbo-Aggregate reduces secure aggregation time from quadratic to nearly linear.

Local AdaAlter reduces communication in SGD with adaptive learning rates.

Deep learning predicts downlink channel from uplink data, reducing signaling overhead.

Efficient FPGA virtualization for deep learning reduces user isolation and overhead.

Paper proposes ADC framework to reduce ViT SL training communication overhead.

SOTERIA optimizes neural networks for secure inference with minimal overhead.

ISAAC Newton uses input-based curvature for efficient training.

HCBM improves deep learning explainability by non-linear concept aggregation.

Generative Adapter adapts LMs with a single forward pass, reducing inference overhead.

Paper uses ML to predict insulator flashover risk.

Meta-learning reduces training overhead for communication systems.

Information-theoretic Bayesian optimisation techniques have demonstrated state-of-the-art performance in tackling important global optimisation problems. However, current information-theoretic approaches require many approximations in implementation, introduce often-prohibitive computational overhead and limit the choi…

Paper introduces zero-space memory protection for CNNs without ECC overhead.

Paper introduces a new adaptive gradient method with gradient compression for distributed training.

Top-k sparsification reduces deep learning communication costs.

Ensuring differential privacy of models learned from sensitive user data is an important goal that has been studied extensively in recent years. It is now known that for some basic learning problems, especially those involving high-dimensional data, producing an accurate private model requires much more data than learn…

Distributed model training suffers from communication overheads due to frequent gradient updates transmitted between compute nodes. To mitigate these overheads, several studies propose the use of sparsified stochastic gradients. We argue that these are facets of a general sparsification method that can operate on any p…

PruneFL reduces FL training time on edge devices by pruning model size.

Sitatapatra blocks adversarial samples across different neural networks.

TorchGAN simplifies GAN training and evaluation with a flexible framework.

TG-PSM morphs encrypted traffic to reduce traffic analysis accuracy.

New method reduces memory usage for adaptive optimization.

A new FL algorithm reduces communication overhead by selectively updating model parameters.

CBC makes CNNs robust against adversarial attacks with minimal computational overhead.

Paper proposes neural network for efficient MIMO channel estimation and pilot reduction.

QPyTorch simplifies low-precision training simulations.

Meta-Neighborhoods adapts predictions based on input neighborhoods.

Distributed implementations of mini-batch stochastic gradient descent (SGD) suffer from communication overheads, attributed to the high frequency of gradient updates inherent in small-batch training. Training with large batches can reduce these overheads; however, large batches can affect the convergence properties and…

Modern information technology services largely depend on cloud infrastructures to provide their services. These cloud infrastructures are built on top of datacenter networks (DCNs) constructed with high-speed links, fast switching gear, and redundancy to offer better flexibility and resiliency. In this environment, net…

A new method for efficient online federated learning reduces communication overhead.

Clapping reduces memory usage in distributed optimization by reusing data samples.

METRO predicts reactions using minimal templates, reducing computational overhead and achieving state-of-the-art results.

New method reduces communication in deep learning training.

One of the most significant bottleneck in training large scale machine learning models on parameter server (PS) is the communication overhead, because it needs to frequently exchange the model gradients between the workers and servers during the training iterations. Gradient quantization has been proposed as an effecti…

TCR improves DNN robustness to noisy labels with minimal overhead.

New method gives high confidence bounds for stochastic convex optimization with minimal overhead.

BayesAdapter turns pre-trained NNs into reliable BNNs with minimal overhead.

TFiLM expands convolutional models' receptive field with minimal overhead.