As a specialized branch of deep learning, Learning to Optimize (L2O) tackles optimization problems by training DNN-based solvers. Despite achieving significant success in various scenarios, such as faster convergence in solving convex optimizations and improved optimality in addressing non-convex cases, there remains a deficiency in theoretical support. Current research heavily relies on stringent assumptions that do not align with the intricacies of the training process. To address this gap, our study aims to establish L2O's convergence through its training methodology. We demonstrate that learning an algorithm's hyperparameters significantly enhances its convergence. Focusing on the gradient descent (GD) algorithm for quadratic programming, we prove the convergence of L2O's training using the neural tangent kernel theory. Moreover, we conduct empirical evaluations using synthetic datasets. Our findings indicate exceeding 50\% outperformance over the GD methods.

Simulation for managing the massive machine learning (ML) clusters is also useful (perhaps more so) to extrapolate beyond what is and large-scale distributed training jobs. In this paper, we currently available, which is paramount for strategic decision build Echo to tackle three key challenges in large-scale training making such as capacity planning [24, 38] that involve many simulation: (1) tracing the runtime training workloads at what-if questions with significant impact. For example, what each device in an ex-situ fashion so we can use a single device speed-up can be achieved by scaling the current cluster by a to obtain the actual execution graphs of 1K-GPU training, (2) factor of 3, or by increasing the network bandwidth by 2x? accurately estimating the collective communication without This also greatly facilitates the development of new optimizations, high overheads of discrete-event based network simulation, which only need to be prototyped on a small scale for and (3) accounting for the interference-induced computation the simulator to extrapolate its potential benefits on a large slowdown from overlapping communication and computation scale quantitatively.

Tuning effective step sizes is crucial for the stability and efficiency of optimization algorithms. While adaptive coordinate-wise step sizes tuning methods have been explored in first-order methods, second-order methods still lack efficient techniques. Current approaches, including hypergradient descent and cutting plane methods, offer limited improvements or encounter difficulties in second-order contexts. To address these challenges, we introduce a novel Learning-to-Optimize (L2O) model within the Broyden-Fletcher-Goldfarb-Shanno (BFGS) framework, which leverages neural networks to predict optimal coordinate-wise step sizes. Our model integrates a theoretical foundation that establishes conditions for the stability and convergence of these step sizes. Extensive experiments demonstrate that our approach achieves substantial improvements over traditional backtracking line search and hypergradient descent-based methods, offering up to 7$\times$ faster and stable performance across diverse optimization tasks.

Large language model (LLM)-based applications consist of both LLM and non-LLM components, each contributing to the end-to-end latency. Despite great efforts to optimize LLM inference, end-to-end workflow optimization has been overlooked. Existing frameworks employ coarse-grained orchestration with task modules, which confines optimizations to within each module and yields suboptimal scheduling decisions. We propose fine-grained end-to-end orchestration, which utilizes task primitives as the basic units and represents each query's workflow as a primitive-level dataflow graph. This explicitly exposes a much larger design space, enables optimizations in parallelization and pipelining across primitives of different modules, and enhances scheduling to improve application-level performance. We build Teola, a novel orchestration framework for LLM-based applications that implements this scheme. Comprehensive experiments show that Teola can achieve up to 2.09x speedup over existing systems across various popular LLM applications.

The capacity of Large Language Models (LLMs) to comprehend and reason over long contexts is pivotal for advancements in diverse fields. Yet, they still stuggle with capturing long-distance dependencies within sequences to deeply understand semantics. To address this issue, we introduce Query-aware Inference for LLMs (Q-LLM), a system designed to process extensive sequences akin to human cognition. By focusing on memory data relevant to a given query, Q-LLM can accurately capture pertinent information within a fixed window size and provide precise answers to queries. It doesn't require extra training and can be seamlessly integrated with any LLMs. Q-LLM using LLaMA3 (QuickLLaMA) can read Harry Potter within 30s and accurately answer the questions. Q-LLM improved by 7.17% compared to the current state-of-the-art on LLaMA3, and by 3.26% on Mistral on the $\infty$-bench. In the Needle-in-a-Haystack task, On widely recognized benchmarks, Q-LLM improved upon the current SOTA by 7.0% on Mistral and achieves 100% on LLaMA3. Our code can be found in https://github.com/dvlab-research/Q-LLM.

The emergence of Large Language Models (LLMs) has improved the prospects for robotic tasks. However, existing benchmarks are still limited to single tasks with limited generalization capabilities. In this work, we introduce a comprehensive benchmark and an autonomous learning framework, RoboCoder aimed at enhancing the generalization capabilities of robots in complex environments. Unlike traditional methods that focus on single-task learning, our research emphasizes the development of a general-purpose robotic coding algorithm that enables robots to leverage basic skills to tackle increasingly complex tasks. The newly proposed benchmark consists of 80 manually designed tasks across 7 distinct entities, testing the models' ability to learn from minimal initial mastery. Initial testing revealed that even advanced models like GPT-4 could only achieve a 47% pass rate in three-shot scenarios with humanoid entities. To address these limitations, the RoboCoder framework integrates Large Language Models (LLMs) with a dynamic learning system that uses real-time environmental feedback to continuously update and refine action codes. This adaptive method showed a remarkable improvement, achieving a 36% relative improvement. Our codes will be released.

Nowadays, Information spreads at an unprecedented pace in social media and discerning truth from misinformation and fake news has become an acute societal challenge. Machine learning (ML) models have been employed to identify fake news but are far from perfect with challenging problems like limited accuracy, interpretability, and generalizability. In this paper, we enhance ML-based solutions with linguistics input and we propose LingML, linguistic-informed ML, for fake news detection. We conducted an experimental study with a popular dataset on fake news during the pandemic. The experiment results show that our proposed solution is highly effective. There are fewer than two errors out of every ten attempts with only linguistic input used in ML and the knowledge is highly explainable. When linguistics input is integrated with advanced large-scale ML models for natural language processing, our solution outperforms existing ones with 1.8% average error rate. LingML creates a new path with linguistics to push the frontier of effective and efficient fake news detection. It also sheds light on real-world multi-disciplinary applications requiring both ML and domain expertise to achieve optimal performance.

Large language models, such as OpenAI's ChatGPT, have demonstrated exceptional language understanding capabilities in various NLP tasks. Sparsely activated mixture-of-experts (MoE) has emerged as a promising solution for scaling models while maintaining a constant number of computational operations. Existing MoE model adopts a fixed gating network where each token is computed by the same number of experts. However, this approach contradicts our intuition that the tokens in each sequence vary in terms of their linguistic complexity and, consequently, require different computational costs. Little is discussed in prior research on the trade-off between computation per token and model performance. This paper introduces adaptive gating in MoE, a flexible training strategy that allows tokens to be processed by a variable number of experts based on expert probability distribution. The proposed framework preserves sparsity while improving training efficiency. Additionally, curriculum learning is leveraged to further reduce training time. Extensive experiments on diverse NLP tasks show that adaptive gating reduces at most 22.5% training time while maintaining inference quality. Moreover, we conduct a comprehensive analysis of the routing decisions and present our insights when adaptive gating is used.

Companies build separate training and inference GPU clusters for deep learning, and use separate schedulers to manage them. This leads to problems for both training and inference: inference clusters have low GPU utilization when the traffic load is low; training jobs often experience long queueing time due to lack of resources. We introduce Aryl, a new cluster scheduler to address these problems. Aryl introduces capacity loaning to loan idle inference GPU servers for training jobs. It further exploits elastic scaling that scales a training job's GPU allocation to better utilize loaned resources. Capacity loaning and elastic scaling create new challenges to cluster management. When the loaned servers need to be returned, we need to minimize the number of job preemptions; when more GPUs become available, we need to allocate them to elastic jobs and minimize the job completion time (JCT). Aryl addresses these combinatorial problems using principled heuristics. It introduces the notion of server preemption cost which it greedily reduces during server reclaiming. It further relies on the JCT reduction value defined for each additional worker for an elastic job to solve the scheduling problem as a multiple-choice knapsack problem. Prototype implementation on a 64-GPU testbed and large-scale simulation with 15-day traces of over 50,000 production jobs show that Aryl brings 1.53x and 1.50x reductions in average queuing time and JCT, and improves cluster usage by up to 26.9% over the cluster scheduler without capacity loaning or elastic scaling.

Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances. In this way, considerable energy savings could be achieved by enhancing household's awareness of energy usage. Recent investigations have shown that deep neural networks (DNNs) based approaches are promising for the NILM task. Nevertheless, they normally ignore the inherent properties of appliance operations in the network design, potentially leading to implausible results. We are thus motivated to develop the dual Deep Neural Networks (dual-DNN), which aims to i) take advantage of DNNs' learning capability of latent features and ii) empower the DNN architecture with identification ability of universal properties. Specifically in the design of dual-DNN, we adopt one subnetwork to measure power ratings of different appliances' operation states, and the other subnetwork to identify the running states of target appliances. The final result is then obtained by multiplying these two network outputs and meanwhile considering the multi-state property of household appliances. To enforce the sparsity property in appliance's state operating, we employ median filtering and hard gating mechanisms to the subnetwork for state identification. Compared with the state-of-the-art NILM methods, our dual-DNN approach demonstrates a 21.67% performance improvement in average on two public benchmark datasets.