Many recent state-of-the-art methods for neural architecture search (NAS) relax the NAS problem into a joint continuous optimization over architecture parameters and their shared-weights, enabling the application of standard gradient-based optimizers. However, this training process remains poorly understood, as evidenced by the multitude of gradient-based heuristics that have been recently proposed. Invoking the theory of mirror descent, we present a unifying framework for designing and analyzing gradient-based NAS methods that exploit the underlying problem structure to quickly find high-performance architectures. Our geometry-aware framework leads to simple yet novel algorithms that (1) enjoy faster convergence guarantees than existing gradient-based methods and (2) achieve state-of-the-art accuracy on the latest NAS benchmarks in computer vision. Notably, we exceed the best published results for both CIFAR and ImageNet on both the DARTS search space and NAS-Bench-201; on the latter benchmark we achieve close to oracle-optimal performance on CIFAR-10 and CIFAR-100. Together, our theory and experiments demonstrate a principled way to co-design optimizers and continuous parameterizations of discrete NAS search spaces.
There exist several inherent trade-offs in designing a fair model, such as those between the model's predictive performance and fairness, or even among different notions of fairness. In practice, exploring these trade-offs requires significant human and computational resources. We propose a diagnostic that enables practitioners to explore these trade-offs without training a single model. Our work hinges on the observation that many widely-used fairness definitions can be expressed via the fairness-confusion tensor, an object obtained by splitting the traditional confusion matrix according to protected data attributes. Optimizing accuracy and fairness objectives directly over the elements in this tensor yields a data-dependent yet model-agnostic way of understanding several types of trade-offs. We further leverage this tensor-based perspective to generalize existing theoretical impossibility results to a wider range of fairness definitions. Finally, we demonstrate the usefulness of the proposed diagnostic on synthetic and real datasets.
A common workflow in data exploration is to learn a low-dimensional representation of the data, identify groups of points in that representation, and examine the differences between the groups to determine what they represent. We treat this as an interpretable machine learning problem by leveraging the model that learned the low-dimensional representation to help identify the key differences between the groups. To solve this problem, we introduce a new type of explanation, a Global Counterfactual Explanation (GCE), and our algorithm, Transitive Global Translations (TGT), for computing GCEs. TGT identifies the differences between each pair of groups using compressed sensing but constrains those pairwise differences to be consistent among all of the groups. Empirically, we demonstrate that TGT is able to identify explanations that accurately explain the model while being relatively sparse, and that these explanations match real patterns in the data.
Federated learning aims to jointly learn statistical models over massively distributed remote devices. In this work, we propose FedDANE, an optimization method that we adapt from DANE, a method for classical distributed optimization, to handle the practical constraints of federated learning. We provide convergence guarantees for this method when learning over both convex and non-convex functions. Despite encouraging theoretical results, we find that the method has underwhelming performance empirically. In particular, through empirical simulations on both synthetic and real-world datasets, FedDANE consistently underperforms baselines of FedAvg and FedProx in realistic federated settings. We identify low device participation and statistical device heterogeneity as two underlying causes of this underwhelming performance, and conclude by suggesting several directions of future work.
Parameter-transfer is a well-known and versatile approach for meta-learning, with applications including few-shot learning, federated learning, and reinforcement learning. However, parameter-transfer algorithms often require sharing models that have been trained on the samples from specific tasks, thus leaving the task-owners susceptible to breaches of privacy. We conduct the first formal study of privacy in this setting and formalize the notion of task-global differential privacy as a practical relaxation of more commonly studied threat models. We then propose a new differentially private algorithm for gradient-based parameter transfer that not only satisfies this privacy requirement but also retains provable transfer learning guarantees in convex settings. Empirically, we apply our analysis to the problem of federated learning with personalization and show that allowing the relaxation to task-global privacy from the more commonly studied notion of local privacy leads to dramatically increased performance in recurrent neural language modeling.
Federated learning involves training statistical models over remote devices or siloed data centers, such as mobile phones or hospitals, while keeping data localized. Training in heterogeneous and potentially massive networks introduces novel challenges that require a fundamental departure from standard approaches for large-scale machine learning, distributed optimization, and privacy-preserving data analysis. In this article, we discuss the unique characteristics and challenges of federated learning, provide a broad overview of current approaches, and outline several directions of future work that are relevant to a wide range of research communities.
Fair representations are a powerful tool for establishing criteria like statistical parity, proxy non-discrimination, and equality of opportunity in learned models. Existing techniques for learning these representations are typically model-agnostic, as they preprocess the original data such that the output satisfies some fairness criterion, and can be used with arbitrary learning methods. In contrast, we demonstrate the promise of learning a model-aware fair representation, focusing on kernel-based models. We leverage the classical Sufficient Dimension Reduction (SDR) framework to construct representations as subspaces of the reproducing kernel Hilbert space (RKHS), whose member functions are guaranteed to satisfy fairness. Our method supports several fairness criteria, continuous and discrete data, and multiple protected attributes. We further show how to calibrate the accuracy tradeoff by characterizing it in terms of the principal angles between subspaces of the RKHS. Finally, we apply our approach to obtain the first Fair Gaussian Process (FGP) prior for fair Bayesian learning, and show that it is competitive with, and in some cases outperforms, state-of-the-art methods on real data.
We build a theoretical framework for understanding practical meta-learning methods that enables the integration of sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms. Our approach enables the task-similarity to be learned adaptively, provides sharper transfer-risk bounds in the setting of statistical learning-to-learn, and leads to straightforward derivations of average-case regret bounds for efficient algorithms in settings where the task-environment changes dynamically or the tasks share a certain geometric structure. We use our theory to modify several popular meta-learning algorithms and improve their training and meta-test-time performance on standard problems in few-shot and federated deep learning.