Related papers: SkillGrad: Optimizing Agent Skills Like Gradient D…

Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic…

Optimizing CUDA code across multiple generations of GPU architectures is challenging, as achieving peak performance requires an extensive exploration of an increasingly complex, hardware-specific optimization space. Traditional compilers…

Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted metrics or static/snapshot-based criteria to estimate…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

We investigate the problem of agent-to-agent interaction in decentralized (federated) learning over time-varying directed graphs, and, in doing so, propose a consensus-based algorithm called DSGTm-TV. The proposed algorithm incorporates…

Current knowledge-enhanced large language models (LLMs) rely on static, pre-constructed knowledge bases that suffer from coverage gaps and temporal obsolescence, limiting their effectiveness in dynamic information environments. We present…

This paper introduces a model-based approach for training feedback controllers for an autonomous agent operating in a highly nonlinear (albeit deterministic) environment. We desire the trained policy to ensure that the agent satisfies…

Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications. However, their performance often degrades in context-specific scenarios, such as…

Existing agents for solving tasks such as ML engineering rely on prompting powerful language models. As a result, these agents do not improve with more experience. In this paper, we show that agents backed by weaker models that improve via…

We propose a novel policy gradient method for multi-agent reinforcement learning, which leverages two different variance-reduction techniques and does not require large batches over iterations. Specifically, we propose a momentum-based…

Large language models (LLMs) are increasingly used in learning algorithms, evaluations, and optimization tasks. Recent studies have shown that using LLM-based optimizers to automatically optimize model prompts, demonstrations, predictions…

LLM-based agents are increasingly used to generate GPU kernels, but they often know what optimizations to try without knowing when those optimizations are sound. We introduce KLineage, which learns this missing "when" knowledge from expert…

Multilevel optimization has gained renewed interest in machine learning due to its promise in applications such as hyperparameter tuning and continual learning. However, existing methods struggle with the inherent difficulty of efficiently…

Stochastic Gradient Descent (SGD) is one of the most widely used techniques for online optimization in machine learning. In this work, we accelerate SGD by adaptively learning how to sample the most useful training examples at each time…

We present the first loss agent, dubbed LossAgent, for low-level image processing tasks, e.g., image super-resolution and restoration, intending to achieve any customized optimization objectives of low-level image processing in different…

This paper studies distributed nonconvex optimization problems with stochastic gradients for a multi-agent system, in which each agent aims to minimize the sum of all agents' cost functions by using local compressed information exchange. We…

As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills,…

In this work, we study an optimizer, Grad-Avg to optimize error functions. We establish the convergence of the sequence of iterates of Grad-Avg mathematically to a minimizer (under boundedness assumption). We apply Grad-Avg along with some…

Policy gradient methods have shown success in learning control policies for high-dimensional dynamical systems. Their biggest downside is the amount of exploration they require before yielding high-performing policies. In a lifelong…

Feature transformation enhances data representation by deriving new features from the original data. Generative AI offers potential for this task, but faces challenges in stable generation (consistent outputs) and valid generation…