​[[{“value”:”This paper was accepted at the Foundation Model Interventions (MINT) Workshop at NeurIPS 2024. Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided guidelines. However, LLMs often fail to follow even simple instructions. To… Read More »Do LLMs Internally “Know” When They Follow Instructions? Apple Machine Learning Research

​We study private stochastic convex optimization (SCO) under user-level differential privacy (DP) constraints. In this setting, there are nnn users, each possessing mmm data items, and we need to protect the privacy of each user’s entire collection of data items. Existing algorithms for user-level DP… Read More »Faster Algorithms for User-Level Private Stochastic Convex Optimization Apple Machine Learning Research

​Learning with identical train and test distributions has been extensively investigated both practically and theoretically. Much remains to be understood, however, in statistical learning under distribution shifts. This paper focuses on a distribution shift setting where train and test distributions can be related by classes… Read More »Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization Apple Machine Learning Research

​[[{“value”:”This paper was accepted at the Safe Generative AI Workshop (SGAIW) at NeurIPS 2024. Large language models (LLMs) could be valuable personal AI agents across various domains, provided they can precisely follow user instructions. However, recent studies have shown significant limitations in LLMs’ instruction-following capabilities,… Read More »Do LLMs Estimate Uncertainty Well in Instruction-Following? Apple Machine Learning Research

​We study the problem of differentially private stochastic convex optimization (DP-SCO) with heavy-tailed gradients, where we assume a kthk^{text{th}}kth-moment bound on the Lipschitz constants of sample functions, rather than a uniform bound. We propose a new reduction-based approach that enables us to obtain the first… Read More »Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions Apple Machine Learning Research

​We study the problem of private online learning, specifically, online prediction from experts (OPE) and online convex optimization (OCO). We propose a new transformation that transforms lazy online learning algorithms into private algorithms. We apply our transformation for differentially private OPE and OCO using existing… Read More »Private Online Learning via Lazy Algorithms Apple Machine Learning Research