Mixture-of-Experts (MoEs) achieve scalability by dynamically activating subsets of their components. Yet, understanding how expertise emerges through joint training of gating mechanisms and experts remains incomplete, especially in scenarios without clear task partitions. Motivated by inference costs and data heterogeneity, we study how joint training of gating functions and experts can dynamically allocate domain-specific expertise across multiple underlying data distributions. As an outcome of our framework, we develop an instance tailored specifically to decentralized training scenarios, introducing *Dynamically Decentralized Orchestration of MoEs* or *DDOME*. *DDOME* leverages heterogeneity emerging from distributional shifts across decentralized data sources to specialize experts dynamically. By integrating a pretrained common expert to inform a gating function, *DDOME* achieves personalized expert subset selection on-the-fly, facilitating just-in-time personalization. We empirically validate *DDOME* within a Federated Learning (FL) context: *DDOME* attains from 4\% up to an 24\% accuracy improvement over state-of-the-art FL baselines in image and text classification tasks, while maintaining competitive zero-shot generalization capabilities. Furthermore, we provide theoretical insights confirming that the joint gating-experts training is critical for achieving meaningful expert specialization.

Current state-of-the-art analyses on the convergence of gradient descent for training neural networks focus on characterizing properties of the loss landscape, such as the Polyak-Lojaciewicz (PL) condition and the restricted strong convexity. While gradient descent converges linearly under such conditions, it remains an open question whether Nesterov’s momentum enjoys accelerated convergence under similar settings and assumptions. In this work, we consider a new class of objective functions, where only a subset of the parameters satisfies strong convexity, and show Nesterov’s momentum achieves acceleration in theory for this objective class. We provide two realizations of the problem class, one of which is deep ReLU networks, which constitutes this work as the first that proves an accelerated convergence rate for non-trivial neural network architectures.

Principal Component Analysis (PCA) aims to find subspaces spanned by the so-called *principal components* that best represent the variance in the dataset. The deflation method is a popular meta-algorithm that sequentially finds individual principal components, starting from the most important ones and working towards the less important ones. However, as deflation proceeds, numerical errors from the imprecise estimation of principal components propagate due to its sequential nature. This paper mathematically characterizes the error propagation of the inexact Hotelling's deflation method. We consider two scenarios: $i)$ when the sub-routine for finding the leading eigenvector is abstract and can represent various algorithms; and $ii)$ when power iteration is used as the sub-routine. In the latter case, the additional directional information from power iteration allows us to obtain a tighter error bound than the sub-routine agnostic case. For both scenarios, we explicitly characterize how the errors progress and affect subsequent principal component estimations.

Recent work on the Lottery Ticket Hypothesis (LTH) shows that there exist “winning tickets” in large neural networks. These tickets represent “sparse” versions of the full model that can be trained independently to achieve comparable accuracy with respect to the full model. However, finding the winning tickets requires one to pretrain the large model for at least a number of epochs, which can be a burdensome task, especially when the original neural network gets larger. In this paper, we explore how one can efficiently identify the emergence of such winning tickets, and use this observation to design efficient pretraining algorithms. For clarity of exposition, our focus is on convolutional neural networks (CNNs). To identify good filters, we propose a novel filter distance metric that well-represents the model convergence. As our theory dictates, our filter analysis behaves consistently with recent findings of neural network learning dynamics. Motivated by these observations, we present the LOttery ticket through Filter-wise Training algorithm, dubbed as LoFT. LoFT is a model-parallel pretraining algorithm that partitions convolutional layers by filters to train them independently in a distributed setting, resulting in reduced memory and communication costs during pretraining. Experiments show that LoFT i) preserves and finds good lottery tickets, while ii) it achieves non-trivial computation and communication savings, and maintains comparable or even better accuracy than other pretraining methods.

Large language models(LLMs) have sparked a new wave of exciting AI applications. Hosting these models at scale requires significant memory resources. One crucial memory bottleneck for the deployment stems from the context window. It is commonly recognized that model weights are memory hungry; however, the size of key-value embedding stored during the generation process (KV cache) can easily surpass the model size. The enormous size of the KV cache puts constraints on the inference batch size, which is crucial for high throughput inference workload. Inspired by an interesting observation of the attention scores, we hypothesize the persistence of importance: only pivotal tokens, which had a substantial influence at one step, will significantly influence future generations. Based on our empirical verification and theoretical analysis around this hypothesis, we propose scissorhands, a system that maintains the memory usage of the KV cache at a fixed budget without finetuning the model. In essence, Scissorhands manages the KV cache by storing the pivotal tokens with a higher probability. We validate that scissorhands reduces the inference memory usage of the KV cache by up to 5$\times$ without compromising model quality. We further demonstrate that scissorhands can be combined with 4-bit quantization, traditionally used to compress model weights, to achieve up to 20$\times$ compression.