Posts in category: Apple

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 lazy algorithms for these problems. Our final algorithms obtain regret which significantly improves the regret in the high privacy regime ε≪1varepsilon ll 1ε≪1, obtaining Tlog⁡d+T1/3log⁡(d)/ε2/3sqrt{T log d} + T^{1/3} log(d)/varepsilon^{2/3}Tlogd​+T1/3log(d)/ε2/3 for…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 optimal rates (up to logarithmic factors) in the heavy-tailed setting, achieving error G2⋅1n+Gk⋅(dnε)1−1kG_2 cdot frac 1 {sqrt n} + G_k cdot (frac{sqrt d}{nvarepsilon})^{1 – frac 1 k}G2​⋅n​1​+Gk​⋅(nεd​​)1−k1​ under (ε,δ)(varepsilon, delta)(ε,δ)-approximate…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 SCO are impractical in many large-scale machine learning scenarios because: (i) they make restrictive assumptions on the smoothness parameter of the loss function and require the number of users to grow polynomially with the dimension of the parameter space; or (ii) they are prohibitively slow…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 of (data) transformation maps. We initiate a theoretical study for this framework, investigating learning scenarios where the target class of transformations is either known or unknown. We establish learning rules and algorithmic reductions to Empirical Risk Minimization…Apple Machine Learning Research

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 improve instruction-following behavior and prevent undesirable outputs, we need a deeper understanding of how LLMs’ internal states relate to these outcomes. Our analysis of LLM internal states reveal a dimension in the input embedding space linked to successful…Apple Machine Learning Research

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024.
Tensor parallelism provides an effective way to increase server large language model (LLM) inference efficiency despite adding an additional communication cost. However, as server LLMs continue to scale in size, they will need to be distributed across more devices, magnifying the communication cost. One way to approach this problem is with quantization, but current methods for LLMs tend to avoid quantizing the features that tensor parallelism needs to communicate. Taking advantage…Apple Machine Learning Research

Large language models (LLMs) are commonly trained on datasets consisting of fixed-length token sequences. These datasets are created by randomly concatenating documents of various lengths and then chunking them into sequences of a predetermined target length (concat-and-chunk). Recent attention implementations mask cross-document attention, reducing the effective length of a chunk of tokens. Additionally, training on long sequences becomes computationally prohibitive due to the quadratic cost of attention. In this study, we introduce dataset decomposition, a novel variable sequence length…Apple Machine Learning Research

This paper was accepted at the Machine Learning and Compression Workshop at NeurIPS 2024.
Compressing Large Language Models (LLMs) often leads to reduced performance, especially for knowledge-intensive tasks. In this work, we dive into how compression damages LLMs’ inherent knowledge and the possible remedies. We start by proposing two conjectures on the nature of the damage: one is certain knowledge being forgotten (or erased) after LLM compression, hence necessitating the compressed model to (re)learn from data with additional parameters; the other presumes that knowledge is internally…Apple Machine Learning Research

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a recurrent neural network (RNN) as the draft model conditioning on LLM’s hidden states, (2) applying a dynamic tree attention algorithm over beam search results to eliminate duplicated prefixes in candidate sequences, and (3) training through knowledge distillation from the LLM. ReDrafter accelerates Vicuna inference in MT-Bench by up to 3.5x with a PyTorch…Apple Machine Learning Research

This paper was accepted at the Efficient Natural Language and Speech Processing (ENLSP) Workshop at NeurIPS 2024.
Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models, speculative decoding, and early exit strategies leverage the insight that computational demands can vary significantly based on the complexity and nature of the input. However, identifying optimal routing patterns for dynamic execution remains an open…Apple Machine Learning Research