Scaling Laws for Downstream Task Performance of Large Language Models

Scaling laws provide important insights that can guide the design of large language models (LLMs). Existing work has primarily focused on studying scaling laws for pretraining (upstream) loss. However, in transfer learning settings, in which LLMs are pretrained on an unsupervised dataset and then finetuned on a downstream task, we often also care about the downstream performance. In this work, we study the scaling behavior in a transfer learning setting, where LLMs are finetuned for machine translation tasks. Specifically, we investigate how the choice of the pretraining data and its size affect downstream performance (translation quality) as judged by two metrics: downstream cross-entropy and BLEU score. Our experiments indicate that the size of the finetuning dataset and the distribution alignment between the pretraining and downstream data significantly influence the scaling behavior. With sufficient alignment, both downstream cross-entropy and BLEU score improve monotonically with more pretraining data. In such cases, we show that it is possible to predict the downstream BLEU score with good accuracy using a log-law. However, there are also cases where moderate misalignment causes the BLEU score to fluctuate or get worse with more pretraining, whereas downstream cross-entropy monotonically improves. By analyzing these observations, we provide new practical insights for choosing appropriate pretraining data.

Measuring Re-identification Risk

Compact user representations (such as embeddings) form the backbone of personalization services. In this work, we present a new theoretical framework to measure re-identification risk in such user representations. Our framework, based on hypothesis testing, formally bounds the probability that an attacker may be able to obtain the identity of a user from their representation. As an application, we show how our framework is general enough to model important real-world applications such as the Chrome's Topics API for interest-based advertising. We complement our theoretical bounds by showing provably good attack algorithms for re-identification that we use to estimate the re-identification risk in the Topics API. We believe this work provides a rigorous and interpretable notion of re-identification risk and a framework to measure it that can be used to inform real-world applications.

How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy

ML models are ubiquitous in real world applications and are a constant focus of research. At the same time, the community has started to realize the importance of protecting the privacy of ML training data. Differential Privacy (DP) has become a gold standard for making formal statements about data anonymization. However, while some adoption of DP has happened in industry, attempts to apply DP to real world complex ML models are still few and far between. The adoption of DP is hindered by limited practical guidance of what DP protection entails, what privacy guarantees to aim for, and the difficulty of achieving good privacy-utility-computation trade-offs for ML models. Tricks for tuning and maximizing performance are scattered among papers or stored in the heads of practitioners. Furthermore, the literature seems to present conflicting evidence on how and whether to apply architectural adjustments and which components are "safe" to use with DP. This work is a self-contained guide that gives an in-depth overview of the field of DP ML and presents information about achieving the best possible DP ML model with rigorous privacy guarantees. Our target audience is both researchers and practitioners. Researchers interested in DP for ML will benefit from a clear overview of current advances and areas for improvement. We include theory-focused sections that highlight important topics such as privacy accounting and its assumptions, and convergence. For a practitioner, we provide a background in DP theory and a clear step-by-step guide for choosing an appropriate privacy definition and approach, implementing DP training, potentially updating the model architecture, and tuning hyperparameters. For both researchers and practitioners, consistently and fully reporting privacy guarantees is critical, and so we propose a set of specific best practices for stating guarantees.

Private Algorithms with Private Predictions

When applying differential privacy to sensitive data, a common way of getting improved performance is to use external information such as other sensitive data, public data, or human priors. We propose to use the algorithms with predictions framework -- previously applied largely to improve time complexity or competitive ratios -- as a powerful way of designing and analyzing privacy-preserving methods that can take advantage of such external information to improve utility. For four important tasks -- quantile release, its extension to multiple quantiles, covariance estimation, and data release -- we construct prediction-dependent differentially private methods whose utility scales with natural measures of prediction quality. The analyses enjoy several advantages, including minimal assumptions about the data, natural ways of adding robustness to noisy predictions, and novel "meta" algorithms that can learn predictions from other (potentially sensitive) data. Overall, our results demonstrate how to enable differentially private algorithms to make use of and learn noisy predictions, which holds great promise for improving utility while preserving privacy across a variety of tasks.

Easy Differentially Private Linear Regression

Linear regression is a fundamental tool for statistical analysis. This has motivated the development of linear regression methods that also satisfy differential privacy and thus guarantee that the learned model reveals little about any one data point used to construct it. However, existing differentially private solutions assume that the end user can easily specify good data bounds and hyperparameters. Both present significant practical obstacles. In this paper, we study an algorithm which uses the exponential mechanism to select a model with high Tukey depth from a collection of non-private regression models. Given $n$ samples of $d$-dimensional data used to train $m$ models, we construct an efficient analogue using an approximate Tukey depth that runs in time $O(d^2n + dm\log(m))$. We find that this algorithm obtains strong empirical performance in the data-rich setting with no data bounds or hyperparameter selection required.

Smooth Anonymity for Sparse Binary Matrices

When working with user data providing well-defined privacy guarantees is paramount. In this work we aim to manipulate and share an entire sparse dataset with a third party privately. In fact, differential privacy has emerged as the gold standard of privacy, however, when it comes to sharing sparse datasets, as one of our main results, we prove that \emph{any} differentially private mechanism that maintains a reasonable similarity with the initial dataset is doomed to have a very weak privacy guarantee. Hence we need to opt for other privacy notions such as $k$-anonymity are better at preserving utility in this context. In this work we present a variation of $k$-anonymity, which we call smooth $k$-anonymity and design simple algorithms that efficiently provide smooth $k$-anonymity. We further perform an empirical evaluation to back our theoretical guarantees, and show that our algorithm improves the performance in downstream machine learning tasks on anonymized data.

Scalable Differentially Private Clustering via Hierarchically Separated Trees

We study the private $k$-median and $k$-means clustering problem in $d$ dimensional Euclidean space. By leveraging tree embeddings, we give an efficient and easy to implement algorithm, that is empirically competitive with state of the art non private methods. We prove that our method computes a solution with cost at most $O(d^{3/2}\log n)\cdot OPT + O(k d^2 \log^2 n / \epsilon^2)$, where $\epsilon$ is the privacy guarantee. (The dimension term, $d$, can be replaced with $O(\log k)$ using standard dimension reduction techniques.) Although the worst-case guarantee is worse than that of state of the art private clustering methods, the algorithm we propose is practical, runs in near-linear, $\tilde{O}(nkd)$, time and scales to tens of millions of points. We also show that our method is amenable to parallelization in large-scale distributed computing environments. In particular we show that our private algorithms can be implemented in logarithmic number of MPC rounds in the sublinear memory regime. Finally, we complement our theoretical analysis with an empirical evaluation demonstrating the algorithm's efficiency and accuracy in comparison to other privacy clustering baselines.

Learning Predictions for Algorithms with Predictions

A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms are designed to take advantage of a possibly-imperfect prediction of some aspect of the problem. While much work has focused on using predictions to improve competitive ratios, running times, or other performance measures, less effort has been devoted to the question of how to obtain the predictions themselves, especially in the critical online setting. We introduce a general design approach for algorithms that learn predictors: (1) identify a functional dependence of the performance measure on the prediction quality, and (2) apply techniques from online learning to learn predictors against adversarial instances, tune robustness-consistency trade-offs, and obtain new statistical guarantees. We demonstrate the effectiveness of our approach at deriving learning algorithms by analyzing methods for bipartite matching, page migration, ski-rental, and job scheduling. In the first and last settings we improve upon existing learning-theoretic results by deriving online results, obtaining better or more general statistical guarantees, and utilizing a much simpler analysis, while in the second and fourth we provide the first learning-theoretic guarantees.

Label differential privacy via clustering

We present new mechanisms for \emph{label differential privacy}, a relaxation of differentially private machine learning that only protects the privacy of the labels in the training set. Our mechanisms cluster the examples in the training set using their (non-private) feature vectors, randomly re-sample each label from examples in the same cluster, and output a training set with noisy labels as well as a modified version of the true loss function. We prove that when the clusters are both large and high-quality, the model that minimizes the modified loss on the noisy training set converges to small excess risk at a rate that is comparable to the rate for non-private learning. We describe both a centralized mechanism in which the entire training set is stored by a trusted curator, and a distributed mechanism where each user stores a single labeled example and replaces her label with the label of a randomly selected user from the same cluster. We also describe a learning problem in which large clusters are necessary to achieve both strong privacy and either good precision or good recall. Our experiments show that randomizing the labels within each cluster significantly improves the privacy vs. accuracy trade-off compared to applying uniform randomized response to the labels, and also compared to learning a model via DP-SGD.