arXiv Machine Learning
Jul 28
Greedy dynamical meta-learning
arXiv:2607. 23925v1 Announce Type: new Abstract: Gradient descent scales well to large models, but becomes unstable over long time horizons.
A New First-Order Meta-Learning Algorithm with Convergence Guarantees
arXiv:2409. 03682v2 Announce Type: replace Abstract: Learning new tasks by leveraging prior experience is a fundamental trait of intelligent systems.
Related stories
Hugging Face Trending Papers
Jul 27
Greedy dynamical meta-learning
Gradient descent scales well to large models, but becomes unstable over long time horizons. Gradient-free optimizers can scale to arbitrary timespans, but are hobbled by high dimensions.
arXiv Machine Learning
Sep 22
Personalized Federated Reinforcement Learning via Model-Agnostic Meta-Learning: Convergence of Exact and Hessian-Free Meta-Policy Gradients
arXiv:2609. 22833v1 Announce Type: new Abstract: We study personalized federated reinforcement learning, in which $n$ agents, each acting in its own Markov decision process, collaborate through a server to learn a shared MAML-style policy initialization that becomes effective for an individual agent once that agent adapts it with a single local policy-gradient step.
arXiv Machine Learning
Jun 16
SILAGE: Memory-Efficient, Full-Gradient-Free Nonconvex Optimization for Nested Finite Sums
arXiv:2606. 15832v1 Announce Type: new Abstract: Empirical risk minimization on massive datasets naturally exhibits a nested double finite-sum structure, where $N=nm$ total samples are logically or physically partitioned into $n$ blocks of size $m$ (e.
arXiv Machine Learning
1d ago
Trust the Direction, Search the Step: Zero-and-First-Order Methods for LLM Fine-Tuning
The paper introduces ZFO, a lightweight framework that separates direction selection from step-size determination in large‑scale neural network optimization. ZFO uses a trusted first‑order optimizer to pick a search direction and then performs only two additional objective evaluations to build a local curvature‑aware model, selecting an adaptive step within a bounded interval. The authors provide theoretical guarantees for reliable curvature estimation, near‑optimal step selection, and convergence to a stationary point, and demonstrate that ZFO improves optimization and final performance over fixed‑step first‑order baselines on language‑model fine‑tuning tasks.
arXiv Machine Learning
Aug 26
TLXML: Task-Level Explanation of Meta-Learning via Influence Functions
arXiv:2501.14271v4 Announce Type: replace Abstract: Meta-learning enables models to rapidly adapt to new tasks by leveraging prior experience, but its adaptation mechanisms remain opaque, especially...
arXiv Machine Learning
Jul 9
Efficient Long-Horizon Learning for Learned Optimization
arXiv:2607. 06772v1 Announce Type: new Abstract: Learned optimization aims to improve upon hand-designed optimizers (e.
arXiv Machine Learning
Jul 2
Zeroth-Order Optimization at the Edge of Stability
arXiv:2604. 14669v2 Announce Type: replace Abstract: Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models, yet their optimization dynamics in deep learning remain underexplored.
arXiv Machine Learning
Aug 4
Simplified Quadratic Gradient: A Unified Framework Bridging Gradient Descent and Newton-Type Methods by Synthesizing Hessians and Gradients
arXiv:2209. 03282v5 Announce Type: replace-cross Abstract: Accelerating the convergence of second-order optimization, particularly Newton-type methods, remains a pivotal challenge in algorithmic research.
arXiv Statistics ML
2d ago
Exact information accounting for SGD methods
arXiv:2610.00446v1 Announce Type: cross Abstract: As an alternative to the standard geometric analyses, we give an exact, information-theoretic analysis of stochastic gradient descent (SGD) and its v...
Hugging Face Trending Papers
Jul 7
Efficient Long-Horizon Learning for Learned Optimization
Learned optimization aims to improve upon hand-designed optimizers (e. g.
OpenAI Blog
Mar 7, 2018
Reptile: A scalable meta-learning algorithm
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the Shortest Descent algorithm to the meta-learning setting, and is mathematically similar to first-order MAML (which is a version of the well-known MAML algorithm) that only needs black-box access to an optimizer such as SGD or Adam, with similar computational efficiency and performance.