ICML 2022 Papers

Recently, speech representation learning has improved many speech-related tasks such as speech recognition, speech classification, and speech-to-text translation. However, all the above tasks are in the direction of speech understanding, but for the inverse direction, speech synthesis, the potential of representation learning is yet to be realized, due to the challenging nature of generating high-quality speech. To address this problem, we propose our framework, Alignment-Aware Acoustic-Text Pretraining (A$^3$T), which reconstructs masked acoustic signals with text input and acoustic-text alignment during training. In this way, the pretrained model can generate high quality reconstructed spectrogram, which can be applied to the speech editing and unseen speaker TTS directly. Experiments show A$^3$T outperforms SOTA models on speech editing, and improves multi-speaker speech synthesis without the external speaker verification model.

We design an algorithm for finding counterfactuals with strong theoretical guarantees on its performance. For any monotone model $f : X^d \to \{0,1\}$ and instance $x^\star$, our algorithm makes \[{S}(f)^{O(\Delta_f(x^\star))}\cdot \log d\]{queries} to $f$ and returns an {\sl optimal} counterfactual for $x^\star$: a nearest instance $x’$ to $x^\star$ for which $f(x’)\ne f(x^\star)$. Here $S(f)$ is the sensitivity of $f$, a discrete analogue of the Lipschitz constant, and $\Delta_f(x^\star)$ is the distance from $x^\star$ to its nearest counterfactuals. The previous best known query complexity was $d^{\,O(\Delta_f(x^\star))}$, achievable by brute-force local search. We further prove a lower bound of $S(f)^{\Omega(\Delta_f(x^\star))} + \Omega(\log d)$ on the query complexity of any algorithm, thereby showing that the guarantees of our algorithm are essentially optimal.

Human learners can readily understand speech, or a melody, when it is presented slower or faster than usual. This paper presents a deep CNN (SITHCon) that uses a logarithmically compressed temporal representation at each level. Because rescaling the time of the input results in a translation of $\log$ time, and because the output of the convolution is invariant to translations, this network can generalize to out-of-sample data that are temporal rescalings of a learned pattern. We compare the performance of SITHCon to a Temporal Convolution Network (TCN) on classification and regression problems with both univariate and multivariate time series. We find that SITHCon, unlike TCN, generalizes robustly over rescalings of about an order of magnitude. Moreover, we show that the network can generalize over exponentially large scales without retraining the weights simply by extending the range of the logarithmically-compressed temporal memory.

It would be useful for machines to use computers as humans do so that they can aid us in everyday tasks. This is a setting in which there is also the potential to leverage large-scale expert demonstrations and human judgements of interactive behaviour, which are two ingredients that have driven much recent success in AI. Here we investigate the setting of computer control using keyboard and mouse, with goals specified via natural language. Instead of focusing on hand-designed curricula and specialized action spaces, we focus on developing a scalable method centered on reinforcement learning combined with behavioural priors informed by actual human-computer interactions. We achieve state-of-the-art and human-level mean performance across all tasks within the MiniWob++ benchmark, a challenging suite of computer control problems, and find strong evidence of cross-task transfer. These results demonstrate the usefulness of a unified human-agent interface when training machines to use computers. Altogether our results suggest a formula for achieving competency beyond MiniWob++ and towards controlling computers, in general, as a human would.

Tensorial Convolutional Neural Networks (TCNNs) have attracted much research attention for their power in reducing model parameters or enhancing the generalization ability. However, exploration of TCNNs is hindered even from weight initialization methods. To be specific, general initialization methods, such as Xavier or Kaiming initialization, usually fail to generate appropriate weights for TCNNs. Meanwhile, although there are ad-hoc approaches for specific architectures (e.g., Tensor Ring Nets), they are not applicable to TCNNs with other tensor decomposition methods (e.g., CP or Tucker decomposition). To address this problem, we propose a universal weight initialization paradigm, which generalizes Xavier and Kaiming methods and can be widely applicable to arbitrary TCNNs. Specifically, we first present the Reproducing Transformation to convert the backward process in TCNNs to an equivalent convolution process. Then, based on the convolution operators in the forward and backward processes, we build a unified paradigm to control the variance of features and gradients in TCNNs. Thus, we can derive fan-in and fan-out initialization for various TCNNs. We demonstrate that our paradigm can stabilize the training of TCNNs, leading to faster convergence and better results.

Meta learning automatically infers an inductive bias, that includes the hyperparameter of the baselearning algorithm, by observing data from a finite number of related tasks. This paper studies PAC-Bayes bounds on meta generalization gap. The meta-generalization gap comprises two sources of generalization gaps: the environmentlevel and task-level gaps resulting from observation of a finite number of tasks and data samples per task, respectively. In this paper, by upper bounding arbitrary convex functions, which link the expected and empirical losses at the environment and also per-task levels, we obtain new PAC-Bayes bounds. Using these bounds, we develop new PAC-Bayes meta-learning algorithms. Numerical examples demonstrate the merits of the proposed novel bounds and algorithm in comparison to prior PAC-Bayes bounds for meta-learning

Accurately estimating personalized treatment effects within a study site (e.g., a hospital) has been challenging due to limited sample size. Furthermore, privacy considerations and lack of resources prevent a site from leveraging subject-level data from other sites. We propose a tree-based model averaging approach to improve the estimation accuracy of conditional average treatment effects (CATE) at a target site by leveraging models derived from other potentially heterogeneous sites, without them sharing subject-level data. To our best knowledge, there is no established model averaging approach for distributed data with a focus on improving the estimation of treatment effects. Specifically, under distributed data networks, our framework provides an interpretable tree-based ensemble of CATE estimators that joins models across study sites, while actively modeling the heterogeneity in data sources through site partitioning. The performance of this approach is demonstrated by a real-world study of the causal effects of oxygen therapy on hospital survival rate and backed up by comprehensive simulation results.

This work studies the classical spectral clustering algorithm which embeds the vertices of some graph G=(V_G, E_G) into R^k using k eigenvectors of some matrix of G, and applies k-means to partition V_G into k clusters. Our first result is a tighter analysis on the performance of spectral clustering, and explains why it works under some much weaker condition than the ones studied in the literature. For the second result, we show that, by applying fewer than k eigenvectors to construct the embedding, spectral clustering is able to produce better output for many practical instances; this result is the first of its kind in spectral clustering. Besides its conceptual and theoretical significance, the practical impact of our work is demonstrated by the empirical analysis on both synthetic and real-world data sets, in which spectral clustering produces comparable or better results with fewer than k eigenvectors.

We study and compare different Graph Neural Network extensions that increase the expressive power of GNNs beyond the Weisfeiler-Leman test. We focus on (i) GNNs based on higher order WL methods, (ii) GNNs that preprocess small substructures in the graph, (iii) GNNs that preprocess the graph up to a small radius, and (iv) GNNs that slightly perturb the graph to compute an embedding. We begin by presenting a simple improvement for this last extension that strictly increases the expressive power of this GNN variant. Then, as our main result, we compare the expressiveness of these extensions to each other through a series of example constructions that can be distinguished by one of the extensions, but not by another one. We also show negative examples that are particularly challenging for each of the extensions, and we prove several claims about the ability of these extensions to count cliques and cycles in the graph.

Covariate-shift generalization, a typical case in out-of-distribution (OOD) generalization, requires a good performance on the unknown test distribution, which varies from the accessible training distribution in the form of covariate shift. Recently, independence-driven importance weighting algorithms in stable learning literature have shown empirical effectiveness to deal with covariate-shift generalization on several learning models, including regression algorithms and deep neural networks, while their theoretical analyses are missing. In this paper, we theoretically prove the effectiveness of such algorithms by explaining them as feature selection processes. We first specify a set of variables, named minimal stable variable set, that is the minimal and optimal set of variables to deal with covariate-shift generalization for common loss functions, such as the mean squared loss and binary cross-entropy loss. Afterward, we prove that under ideal conditions, independence-driven importance weighting algorithms could identify the variables in this set. Analysis of asymptotic properties is also provided. These theories are further validated in several synthetic experiments.

The policy gradient theorem (Sutton et al., 2000) prescribes the usage of a cumulative discounted state distribution under the target policy to approximate the gradient. Most algorithms based on this theorem, in practice, break this assumption, introducing a distribution shift that can cause the convergence to poor solutions. In this paper, we propose a new approach of reconstructing the policy gradient from the start state without requiring a particular sampling strategy. The policy gradient calculation in this form can be simplified in terms of a gradient critic, which can be recursively estimated due to a new Bellman equation of gradients. By using temporal-difference updates of the gradient critic from an off-policy data stream, we develop the first estimator that side-steps the distribution shift issue in a model-free way. We prove that, under certain realizability conditions, our estimator is unbiased regardless of the sampling strategy. We empirically show that our technique achieves a superior bias-variance trade-off and performance in presence of off-policy samples.

Winning lottery tickets refer to sparse subgraphs of deep neural networks which have classification accuracy close to the original dense networks. Resilient connectivity properties of such sparse networks play an important role in their performance. The attempt is to identify a sparse and yet well-connected network to guarantee unhindered information flow. Connectivity in a graph is best characterized by its spectral expansion property. Ramanujan graphs are robust expanders which lead to sparse but highly-connected networks, and thus aid in studying the winning tickets. A feedforward neural network consists of a sequence of bipartite graphs representing its layers. We analyze the Ramanujan graph property of such bipartite layers in terms of their spectral characteristics using the Cheeger’s inequality for irregular graphs. It is empirically observed that the winning ticket networks preserve the Ramanujan graph property and achieve a high accuracy even when the layers are sparse. Accuracy and robustness to noise start declining as many of the layers lose the property. Next we find a robust winning lottery ticket by pruning individual layers while retaining their respective Ramanujan graph property. This strategy is observed to improve the performance of existing network pruning algorithms.

Face obfuscation (blurring, mosaicing, etc.) has been shown to be effective for privacy protection; nevertheless, object recognition research typically assumes access to complete, unobfuscated images. In this paper, we explore the effects of face obfuscation on the popular ImageNet challenge visual recognition benchmark. Most categories in the ImageNet challenge are not people categories; however, many incidental people appear in the images, and their privacy is a concern. We first annotate faces in the dataset. Then we demonstrate that face obfuscation has minimal impact on the accuracy of recognition models. Concretely, we benchmark multiple deep neural networks on obfuscated images and observe that the overall recognition accuracy drops only slightly (<= 1.0%). Further, we experiment with transfer learning to 4 downstream tasks (object recognition, scene recognition, face attribute classification, and object detection) and show that features learned on obfuscated images are equally transferable. Our work demonstrates the feasibility of privacy-aware visual recognition, improves the highly-used ImageNet challenge benchmark, and suggests an important path for future visual datasets. Data and code are available at https://github.com/princetonvisualai/imagenet-face-obfuscation.

In modern machine learning systems, distributed algorithms are deployed across applications to ensure data privacy and optimal utilization of computational resources. This work offers a fresh perspective to model, analyze, and design distributed optimization algorithms through the lens of stochastic multi-rate feedback control. We show that a substantial class of distributed algorithms—including popular Gradient Tracking for decentralized learning, and FedPD and Scaffold for federated learning—can be modeled as a certain discrete-time stochastic feedback-control system, possibly with multiple sampling rates. This key observation allows us to develop a generic framework to analyze the convergence of the entire algorithm class. It also enables one to easily add desirable features such as differential privacy guarantees, or to deal with practical settings such as partial agent participation, communication compression, and imperfect communication in algorithm design and analysis.

Many problems in machine learning involve data sets in which each data point is a point cloud in $\mathbb{R}^D$. A growing number of applications require a means of measuring not only distances between point clouds, but also angles, volumes, derivatives, and other more advanced concepts. To formulate and quantify these concepts in a coordinate-invariant way, we develop a Riemannian geometric framework for point cloud data. By interpreting each point in a point cloud as a sample drawn from some given underlying probability density, the space of point cloud data can be given the structure of a statistical manifold – each point on this manifold represents a point cloud – with the Fisher information metric acting as a natural Riemannian metric. Two autoencoder applications of our framework are presented: (i) smoothly deforming one 3D object into another via interpolation between the two corresponding point clouds; (ii) learning an optimal set of latent space coordinates for point cloud data that best preserves angles and distances, and thus produces a more discriminative representation space. Experiments with large-scale standard benchmark point cloud data show greatly improved classification accuracy vis-á-vis existing methods. Code is available at https://github.com/seungyeon-k/SMF-public.

While reinforcement learning (RL) provides a framework for learning through trial and error, translating RL algorithms into the real world has remained challenging. A major hurdle to real-world application arises from the development of algorithms in an episodic setting where the environment is reset after every trial, in contrast with the continual and non-episodic nature of the real-world encountered by embodied agents such as humans and robots. Enabling agents to learn behaviors autonomously in such non-episodic environments requires that the agent to be able to conduct its own trials. Prior works have considered an alternating approach where a forward policy learns to solve the task and the backward policy learns to reset the environment, but what initial state distribution should the backward policy reset the agent to? Assuming access to a few demonstrations, we propose a new method, MEDAL, that trains the backward policy to match the state distribution in the provided demonstrations. This keeps the agent close to the task-relevant states, allowing for a mix of easy and difficult starting states for the forward policy. Our experiments show that MEDAL matches or outperforms prior methods on three sparse-reward continuous control tasks from the EARL benchmark, with 40% gains on the hardest task, while making fewer assumptions than prior works.

Nonconvex constrained optimization problems can be used to model a number of machine learning problems, such as multi-class Neyman-Pearson classification and constrained Markov decision processes. However, such kinds of problems are challenging because both the objective and constraints are possibly nonconvex, so it is difficult to balance the reduction of the loss value and reduction of constraint violation. Although there are a few methods that solve this class of problems, all of them are double-loop or triple-loop algorithms, and they require oracles to solve some subproblems up to certain accuracy by tuning multiple hyperparameters at each iteration. In this paper, we propose a novel gradient descent and perturbed ascent (GDPA) algorithm to solve a class of smooth nonconvex inequality constrained problems. The GDPA is a primal-dual algorithm, which only exploits the first-order information of both the objective and constraint functions to update the primal and dual variables in an alternating way. The key feature of the proposed algorithm is that it is a single-loop algorithm, where only two step-sizes need to be tuned. We show that under a mild regularity condition GDPA is able to find Karush-Kuhn-Tucker (KKT) points of nonconvex functional constrained problems with convergence rate guarantees. To the best of our knowledge, it is the first single-loop algorithm that can solve the general nonconvex smooth problems with nonconvex inequality constraints. Numerical results also showcase the superiority of GDPA compared with the best-known algorithms (in terms of both stationarity measure and feasibility of the obtained solutions).

Stochastic high dimensional bandit problems with low dimensional structures are useful in different applications such as online advertising and drug discovery. In this work, we propose a simple unified algorithm for such problems and present a general analysis framework for the regret upper bound of our algorithm. We show that under some mild unified assumptions, our algorithm can be applied to different high-dimensional bandit problems. Our framework utilizes the low dimensional structure to guide the parameter estimation in the problem, therefore our algorithm achieves the comparable regret bounds in the LASSO bandit as a sanity check, as well as novel bounds that depend logarithmically on dimensions in the low-rank matrix bandit, the group sparse matrix bandit, and in a new problem: the multi-agent LASSO bandit.

In constrained reinforcement learning (RL), a learning agent seeks to not only optimize the overall reward but also satisfy the additional safety, diversity, or budget constraints. Consequently, existing constrained RL solutions require several new algorithmic ingredients that are notably different from standard RL. On the other hand, reward-free RL is independently developed in the unconstrained literature, which learns the transition dynamics without using the reward information, and thus naturally capable of addressing RL with multiple objectives under the common dynamics. This paper bridges reward-free RL and constrained RL. Particularly, we propose a simple meta-algorithm such that given any reward-free RL oracle, the approachability and constrained RL problems can be directly solved with negligible overheads in sample complexity. Utilizing the existing reward-free RL solvers, our framework provides sharp sample complexity results for constrained RL in the tabular MDP setting, matching the best existing results up to a factor of horizon dependence; our framework directly extends to a setting of tabular two-player Markov games, and gives a new result for constrained RL with linear function approximation.