Specifications for decentralized learning on resource-constrained edge devices require algorithms that are communication-efficient, robust to data corruption, and lightweight in memory usage. While state-of-the-art gossip-based methods satisfy the first requirement, achieving robustness remains challenging. Asynchronous decentralized ADMM-based methods have been explored for estimating the median, a statistical centrality measure that is notoriously more robust than the mean. However, existing approaches require memory that scales with node degree, making them impractical when memory is limited. In this paper, we propose AsylADMM, a novel gossip algorithm for decentralized median and quantile estimation, primarily designed for asynchronous updates and requiring only two variables per node. We analyze a synchronous variant of AsylADMM to establish theoretical guarantees and empirically demonstrate fast convergence for the asynchronous algorithm. We then show that our algorithm enables quantile-based trimming, geometric median estimation, and depth-based trimming, with quantile-based trimming empirically outperforming existing rank-based methods. Finally, we provide a novel theoretical analysis of rank-based trimming via Markov chain theory.

We analyze new online gradient descent algorithms for distributed systems with large delays between gradient computations and the corresponding updates. Using insights from adaptive gradient methods, we develop algorithms that adapt not only to the sequence of gradients, but also to the precise update delays that occur. We first give an impractical algorithm that achieves a regret bound that precisely quantifies the impact of the delays. We then analyze AdaptiveRevision, an algorithm that is efficiently implementable and achieves comparable guarantees. The key algorithmic technique is appropriately and efficiently revising the learning rate used for previous gradient steps. Experimental results show when the delays grow large (1000 updates or more), our new algorithms perform significantly better than standard adaptive gradient methods.

While Sharpness-Aware Minimization (SAM) improves generalization in deep neural networks by minimizing both loss and sharpness, it suffers from inefficiency in distributed large-batch training. We present Landscape-Smoothed SAM (LSAM), a novel optimizer that preserves SAM's generalization advantages while offering superior efficiency. LSAM integrates SAM's adversarial steps with an asynchronous distributed sampling strategy, generating an asynchronous distributed sampling scheme, producing a smoothed sharpness-aware loss landscape for optimization. This design eliminates synchronization bottlenecks, accelerates large-batch convergence, and delivers higher final accuracy compared to data-parallel SAM.

HARP 2.0 brings deep learning models to digital audio workstation (DAW) software through hosted, asynchronous, remote processing, allowing users to route audio from a plug-in interface through any compatible Gradio endpoint to perform arbitrary transformations. HARP renders endpoint-defined controls and processed audio in-plugin, meaning users can explore a variety of cutting-edge deep learning models without ever leaving the DAW. In the 2.0 release we introduce support for MIDI-based models and audio/MIDI labeling models, provide a streamlined pyharp Python API for model developers, and implement numerous interface and stability improvements. Through this work, we hope to bridge the gap between model developers and creatives, improving access to deep learning models by seamlessly integrating them into DAW workflows.

We analyze new online gradient descent algorithms for distributed systems with large delays between gradient computations and the corresponding updates. Using insights from adaptive gradient methods, we develop algorithms that adapt not only to the sequence of gradients, but also to the precise update delays that occur. We first give an impractical algorithm that achieves a regret bound that precisely quantifies the impact of the delays. We then analyze AdaptiveRevision, an algorithm that is efficiently implementable and achieves comparable guarantees. The key algorithmic technique is appropriately and efficiently revising the learning rate used for previous gradient steps.

Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT's performance in the task of implicit discourse relation classification, prompted by a standard multiple-choice question, is still far from satisfactory and considerably inferior to state-of-the-art supervised approaches. This work investigates several proven prompting techniques to improve ChatGPT's recognition of discourse relations. In particular, we experimented with breaking down the classification task that involves numerous abstract labels into smaller subtasks. Nonetheless, experiment results show that the inference accuracy hardly changes even with sophisticated prompt engineering, suggesting that implicit discourse relation classification is not yet resolvable under zero-shot or few-shot settings.

In this paper we present a fully distributed, asynchronous, and general purpose optimization algorithm for Consensus Simultaneous Localization and Mapping (CSLAM). Multi-robot teams require that agents have timely and accurate solutions to their state as well as the states of the other robots in the team. To optimize this solution we develop a CSLAM back-end based on Consensus ADMM called MESA (Manifold, Edge-based, Separable ADMM). MESA is fully distributed to tolerate failures of individual robots, asynchronous to tolerate practical network conditions, and general purpose to handle any CSLAM problem formulation. We demonstrate that MESA exhibits superior convergence rates and accuracy compare to existing state-of-the art CSLAM back-end optimizers.

Distributed learning is a problem of fundamental interest in machine learning and cognitive science. In this paper, we present asynchronous distributed learning algorithms for two well-known unsupervised learning frameworks: Latent Dirichlet Allocation (LDA) and Hierarchical Dirichlet Processes (HDP). In the proposed approach, the data are distributed across P processors, and processors independently perform Gibbs sampling on their local data and communicate their information in a local asynchronous manner with other processors. We demonstrate that our asynchronous algorithms are able to learn global topic models that are statistically as accurate as those learned by the standard LDA and HDP samplers, but with significant improvements in computation time and memory. We show speedup results on a 730-million-word text corpus using 32 processors, and we provide perplexity results for up to 1500 virtual processors.

Asynchronous learning protocols have regained attention lately, especially in the Federated Learning (FL) setup, where slower clients can severely impede the learning process. Herein, we propose \texttt{AsyncDrop}, a novel asynchronous FL framework that utilizes dropout regularization to handle device heterogeneity in distributed settings. Overall, \texttt{AsyncDrop} achieves better performance compared to state of the art asynchronous methodologies, while resulting in less communication and training time overheads. The key idea revolves around creating ``submodels'' out of the global model, and distributing their training to workers, based on device heterogeneity. We rigorously justify that such an approach can be theoretically characterized. We implement our approach and compare it against other asynchronous baselines, both by design and by adapting existing synchronous FL algorithms to asynchronous scenarios. Empirically, \texttt{AsyncDrop} reduces the communication cost and training time, while matching or improving the final test accuracy in diverse non-i.i.d. FL scenarios.

Memories of school tend to be one of the best recollections for many people, with reminiscences like attending your favorite teacher's class or lessons learned that have changed our lives for the better. Recently, there has been tremendous technological progress in every sector over the years, and education is no exception. Educators play an integral role in inspiring and motivating students, and in the current setting, they have created and adopted exceptional innovation and transformational methods in the world of educational technology (EdTech). The learning process has been in a continuous state of evolution and the classroom anatomy has drastically changed. In addition to impacting the education industry significantly, the Covid-19 pandemic sparked an urgent digital revolution in this sector.