Related papers: Stop talking to me -- a communication-avoiding ADE…

A numerical method ADER-DG with a local DG predictor for solving a DAE system has been developed, which was based on the formulation of ADER-DG methods using a local DG predictor for solving ODE and PDE systems. The basis functions were…

End-to-end approaches for automatic speech recognition (ASR) benefit from directly modeling the probability of the word sequence given the input audio stream in a single neural network. However, compared to conventional ASR systems, these…

Parallel applications with irregular and time-varying workloads often suffer from load imbalance. Dynamic load balancing techniques address this challenge by redistributing work during execution. We present a new type of distributed…

Wearable devices like smart glasses are approaching the compute capability to seamlessly generate real-time closed captions for live conversations. We build on our recently introduced directional Automatic Speech Recognition (ASR) for smart…

We present Speaking Memories, a distributed, stakeholder-in-the-loop robotic interaction platform for personalized cognitive exercise support. Rather than a single robot-centric system, Speaking Memories is designed as a generalizable…

In recent years, multiple sensor-based devices and systems have been deployed in smart agriculture, industrial automation, E-Health, etc. The diversity of sensor data types and the amount of data pose critical challenges for data…

Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…

This paper presents a high-order discontinuous Galerkin finite element method to solve the barotropic version of the conservative symmetric hyperbolic and thermodynamically compatible (SHTC) model of compressible two-phase flow, introduced…

Many empirical studies have provided evidence for the emergence of algorithmic mechanisms (abilities) in the learning of language models, that lead to qualitative improvements of the model capabilities. Yet, a theoretical characterization…

When gradient descent (GD) is scaled to many parallel workers for large scale machine learning problems, its per-iteration computation time is limited by the straggling workers. Straggling workers can be tolerated by assigning redundant…

The paper focuses on the development of numerical methods for the compressible Euler equations. It is well-known that if the Mach number is small, the system becomes stiff and hence explicit schemes suffer from severe time-step…

We analyze (stochastic) gradient descent (SGD) with delayed updates on smooth quasi-convex and non-convex functions and derive concise, non-asymptotic, convergence rates. We show that the rate of convergence in all cases consists of two…

Recurrent-attention hybrids aim to combine the efficiency of recurrence with the expressivity of attention, but existing approaches typically apply attention uniformly across all positions, even when the recurrent state alone is sufficient…

Transformer encoder-decoder models have achieved great performance in dialogue generation tasks, however, their inability to process long dialogue history often leads to truncation of the context To address this problem, we propose a novel…

While existing text-to-speech (TTS) models exhibit high expressiveness, fine-grained control over composite instructions remains challenging due to the structural mismatch between discrete textual intents and continuous acoustic…

Differentially private stochastic gradient descent (DP-SGD) adds noise to gradients in back-propagation, safeguarding training data from privacy leakage, particularly membership inference. It fails to cover (inference-time) threats like…

Recognizing emotions in spoken communication is crucial for advanced human-machine interaction. Current emotion detection methodologies often display biases when applied cross-corpus. To address this, our study amalgamates 16 diverse…

Discontinuous Galerkin (DG) methods for hyperbolic partial differential equations (PDEs) with explicit time-stepping schemes, such as strong stability-preserving Runge-Kutta (SSP-RK), suffer from time-step restrictions that are…

We propose a distributed algorithm, named Distributed Alternating Direction Method of Multipliers (D-ADMM), for solving separable optimization problems in networks of interconnected nodes or agents. In a separable optimization problem there…

In this paper, we analyze the preservation of asymptotic properties of partially dissipative hyperbolic systems when switching to a discrete setting. We prove that one of the simplest consistent and unconditionally stable numerical methods…