7 articles tagged with #convergence-theory. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers propose q-PDGD, a quantized stochastic primal-dual optimization method for distributed systems with limited communication bandwidth. The approach achieves linear convergence under relaxed geometric conditions and matches centralized stochastic optimization rates while reducing communication overhead through quantization.
Researchers prove that Monte Carlo optimistic policy iteration converges to optimal solutions under more practical conditions than previously known, relaxing the requirement for uniform initialization across the entire state-action space to only requiring uniformity within each state's actions. This theoretical advance enables scalable reinforcement learning implementations when state spaces are large or unknown.
Researchers introduce GAMBLe, a framework for analyzing AI-Driven Research Systems (ADRS) that couple large language models with automated evaluation. Through 760+ experiments, the framework reveals that standard convergence guarantees fail to capture ADRS behavior, and component selection can improve performance by 13-67% depending on the problem.
Researchers introduce a new class of asynchronous adaptive first-order optimization methods that improve upon existing algorithms through momentum and inexact normalization variants. The methods achieve O(1/√t) convergence rates in stochastic non-convex settings and demonstrate practical relevance for large-scale heterogeneous machine learning systems.
Researchers present a unified mathematical framework for gradient aggregation in multi-objective optimization (MOO), establishing convergence guarantees to Pareto stationarity. The work reveals that non-conflicting gradient directions within the convex hull satisfy sufficient conditions for convergence, enabling broader algorithmic approaches including a new method called capped MGDA for federated learning applications.
Researchers introduce intrinsic Muon (iMuon), a unified optimization framework that extends the Muon optimizer to Riemannian manifolds while preserving symmetries and enabling closed-form solutions. The approach demonstrates applications in LLM fine-tuning, image classification, and subspace learning with convergence guarantees dependent only on manifold dimension rather than factor conditioning.
Researchers introduce HilbNets, a novel deep learning framework that handles infinite-dimensional signals (like time series and probability distributions) on irregular domains using Hilbert bundles and cellular sheaves. The work provides theoretical convergence guarantees and demonstrates that discretized networks maintain consistency across different data sampling schemes, advancing geometric deep learning theory.
