ICML 2023 论文列表

Recent studies have revealed the intriguing few-shot learning ability of pretrained language models (PLMs): They can quickly adapt to a new task when fine-tuned on a small amount of labeled data formulated as prompts, without requiring abundant task-specific annotations. Despite their promising performance, most existing few-shot approaches that only learn from the small training set still underperform fully supervised training by nontrivial margins. In this work, we study few-shot learning with PLMs from a different perspective: We first tune an autoregressive PLM on the few-shot samples and then use it as a generator to synthesize a large amount of novel training samples which augment the original training set. To encourage the generator to produce label-discriminative samples, we train it via weighted maximum likelihood where the weight of each token is automatically adjusted based on a discriminative meta-learning objective. A classification PLM can then be fine-tuned on both the few-shot and the synthetic samples with regularization for better generalization and stability. Our approach FewGen achieves an overall better result across seven classification tasks of the GLUE benchmark than existing few-shot learning methods, improving no-augmentation methods by 5+ average points, and outperforming augmentation methods by 3+ average points.

Diffusion models have exhibited excellent performance in various domains. The probability flow ordinary differential equation (ODE) of diffusion models (i.e., diffusion ODEs) is a particular case of continuous normalizing flows (CNFs), which enables deterministic inference and exact likelihood evaluation. However, the likelihood estimation results by diffusion ODEs are still far from those of the state-of-the-art likelihood-based generative models. In this work, we propose several improved techniques for maximum likelihood estimation for diffusion ODEs, including both training and evaluation perspectives. For training, we propose velocity parameterization and explore variance reduction techniques for faster convergence. We also derive an error-bounded high-order flow matching objective for finetuning, which improves the ODE likelihood and smooths its trajectory. For evaluation, we propose a novel training-free truncated-normal dequantization to fill the training-evaluation gap commonly existing in diffusion ODEs. Building upon these techniques, we achieve state-of-the-art likelihood estimation results on image datasets (2.56 on CIFAR-10, 3.43/3.69 on ImageNet-32) without variational dequantization or data augmentation.

We present a new distribution-free conformal prediction algorithm for sequential data (e.g., time series), called the *sequential predictive conformal inference* (SPCI). We specifically account for the nature that time series data are non-exchangeable, and thus many existing conformal prediction algorithms are not applicable. The main idea is to adaptively re-estimate the conditional quantile of non-conformity scores (e.g., prediction residuals), upon exploiting the temporal dependence among them. More precisely, we cast the problem of conformal prediction interval as predicting the quantile of a future residual, given a user-specified point prediction algorithm. Theoretically, we establish asymptotic valid conditional coverage upon extending consistency analyses in quantile regression. Using simulation and real-data experiments, we demonstrate a significant reduction in interval width of SPCI compared to other existing methods under the desired empirical coverage.

We study the problem of (learning) algorithm comparison, where the goal is to find differences between models trained with two different learning algorithms. We begin by formalizing this goal as one of finding distinguishing feature transformations, i.e., input transformations that change the predictions of models trained with one learning algorithm but not the other. We then present ModelDiff, a method that leverages the datamodels framework (Ilyas et al., 2022) to compare learning algorithms based on how they use their training data. We demonstrate ModelDiff through three case studies, comparing models trained with/without data augmentation, with/without pre-training, and with different SGD hyperparameters.

Discovering knowledge about which types of events influence others, using datasets of event sequences without time stamps, has several practical applications. While neural sequence models are able to capture complex and potentially long-range historical dependencies, they often lack the interpretability of simpler models for event sequence dynamics. We provide a novel neural framework in such a setting - a probabilistic attention-to-influence neural model - which not only captures complex instance-wise interactions between events but also learns influencers for each event type of interest. Given event sequence data and a prior distribution on type-wise influence, we efficiently learn an approximate posterior for type-wise influence by an attention-to-influence transformation using variational inference. Our method subsequently models the conditional likelihood of sequences by sampling the above posterior to focus attention on influencing event types. We motivate our general framework and show improved performance in experiments compared to existing baselines on synthetic data as well as real-world benchmarks, for tasks involving prediction and influencing set identification.

In this paper, we present efficient quantum algorithms that are exponentially faster than classical algorithms for solving the quantum optimal control problem. This problem involves finding the control variable that maximizes a physical quantity at time $T$, where the system is governed by a time-dependent Schrödinger equation. This type of control problem also has an intricate relation with machine learning. Our algorithms are based on a time-dependent Hamiltonian simulation method and a fast gradient-estimation algorithm. We also provide a comprehensive error analysis to quantify the total error from various steps, such as the finite-dimensional representation of the control function, the discretization of the Schrödinger equation, the numerical quadrature, and optimization. Our quantum algorithms require fault-tolerant quantum computers.

Partial label learning (PLL) aims to train multiclass classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct. In the last few years, the instance-independent generation process of candidate labels has been extensively studied, on the basis of which many theoretical advances have been made in PLL. Nevertheless, the candidate labels are always instance-dependent in practice and there is no theoretical guarantee that the model trained on the instance-dependent PLL examples can converge to an ideal one. In this paper, a theoretically grounded and practically effective approach named POP, i.e. PrOgressive Purification for instance-dependent partial label learning, is proposed. Specifically, POP updates the learning model and purifies each candidate label set progressively in every epoch. Theoretically, we prove that POP enlarges the region appropriately fast where the model is reliable, and eventually approximates the Bayes optimal classifier with mild assumptions. Technically, POP is flexible with arbitrary PLL losses and could improve the performance of the previous PLL losses in the instance-dependent case. Experiments on the benchmark datasets and the real-world datasets validate the effectiveness of the proposed method.

Latent variable models are powerful tools for modeling complex phenomena involving in particular partially observed data, unobserved variables or underlying complex unknown structures. Inference is often difficult due to the latent structure of the model. To deal with parameter estimation in the presence of latent variables, well-known efficient methods exist, such as gradient-based and EM-type algorithms, but with practical and theoretical limitations. In this paper, we propose as an alternative for parameter estimation an efficient preconditioned stochastic gradient algorithm. Our method includes a preconditioning step based on a positive definite Fisher information matrix estimate. We prove convergence results for the proposed algorithm under mild assumptions for very general latent variables models. We illustrate through relevant simulations the performance of the proposed methodology in a nonlinear mixed effects model and in a stochastic block model.

Deep neural networks (DNNs) have been found to be vulnerable to backdoor attacks, raising security concerns about their deployment in mission-critical applications. While existing defense methods have demonstrated promising results, it is still not clear how to effectively remove backdoor-associated neurons in backdoored DNNs. In this paper, we propose a novel defense called *Reconstructive Neuron Pruning* (RNP) to expose and prune backdoor neurons via an unlearning and then recovering process. Specifically, RNP first unlearns the neurons by maximizing the model's error on a small subset of clean samples and then recovers the neurons by minimizing the model's error on the same data. In RNP, unlearning is operated at the neuron level while recovering is operated at the filter level, forming an asymmetric reconstructive learning procedure. We show that such an asymmetric process on only a few clean samples can effectively expose and prune the backdoor neurons implanted by a wide range of attacks, achieving a new state-of-the-art defense performance. Moreover, the unlearned model at the intermediate step of our RNP can be directly used to improve other backdoor defense tasks including backdoor removal, trigger recovery, backdoor label detection, and backdoor sample detection. Code is available at https://github.com/bboylyg/RNP.

In this paper, we study the $k$-clustering problems with outliers in distributed setting. The current best results for the distributed $k$-center problem with outliers have quadratic local running time with communication cost dependent on the aspect ratio $\Delta$ of the given instance, which may constraint the scalability of the algorithms for handling large-scale datasets. To achieve better communication cost for the problem with faster local running time, we propose an inliers-recalling sampling method, which avoids guessing the optimal radius of the given instance, and can achieve a 4-round bi-criteria $(14(1+\epsilon),1+\epsilon)$-approximation with linear local running time in the data size and communication cost independent of the aspect ratio. To obtain a more practical algorithm for the problem, we propose another space-narrowing sampling method, which automatically adjusts the sample size to adapt to different outliers distributions on each machine, and can achieve a 2-round bi-criteria $(14(1+\epsilon),1+\epsilon)$-approximation with communication cost independent of the number of outliers. We show that, if the data points are randomly partitioned across machines, our proposed sampling-based methods can be extended to the $k$-median/means problems with outliers, and can achieve $(O(\frac{1}{\epsilon^2}),1+\epsilon)$-approximation with communication cost independent of the number of outliers. Empirical experiments suggest that the proposed 2-round distributed algorithms outperform other state-of-the-art algorithms.

Human dexterity is a hallmark of motor control behaviors. Our hands can rapidly synthesize new behaviors despite the complexity (multi-articular and multi-joints, with 23 joints controlled by more than 40 muscles) of mosculoskeletal control. In this work, we take inspiration from how human dexterity builds on a diversity of prior experiences, instead of being acquired through a single task. Motivated by this observation, we set out to develop agents that can build upon previous experience to quickly acquire new (previously unattainable) behaviors. Specifically, our approach leverages multi-task learning to implicitly capture a task-agnostic behavioral priors (MyoDex) for human-like dexterity, using a physiologically realistic human hand model -- MyoHand. We demonstrate MyoDex's effectiveness in few-shot generalization as well as positive transfer to a large repertoire of unseen dexterous manipulation tasks. MyoDex can solve approximately 3x more tasks and it can accelerate the achievement of solutions by about 4x in comparison to a distillation baseline. While prior work has synthesized single musculoskeletal control behaviors, MyoDex is the first generalizable manipulation prior that catalyzes the learning of dexterous physiological control across a large variety of contact-rich behaviors.

Lossy image compression aims to represent images in as few bits as possible while maintaining fidelity to the original. Theoretical results indicate that optimizing distortion metrics such as PSNR or MS-SSIM necessarily leads to a discrepancy in the statistics of original images from those of reconstructions, in particular at low bitrates, often manifested by the blurring of the compressed images. Previous work has leveraged adversarial discriminators to improve statistical fidelity. Yet these binary discriminators adopted from generative modeling tasks may not be ideal for image compression. In this paper, we introduce a non-binary discriminator that is conditioned on quantized local image representations obtained via VQ-VAE autoencoders. Our evaluations on the CLIC2020, DIV2K and Kodak datasets show that our discriminator is more effective for jointly optimizing distortion (e.g., PSNR) and statistical fidelity (e.g., FID) than the PatchGAN of the state-of-the-art HiFiC model. On CLIC2020, we obtain the same FID as HiFiC with 30-40% fewer bits.

Quantization methods reduce the number of bits required to represent each parameter in a model, trading accuracy for smaller memory footprints and inference latencies. However, the final model size depends on both the number of parameters of the original model and the rate of compression. For example, a 30B 8-bit model and a 60B 4-bit model have the same number of bits but may have very different zero-shot accuracies. In this work, we study this trade-off by developing inference scaling laws of zero-shot performance in Large Language Models (LLMs) to determine the bit-precision and model size that maximizes zero-shot performance. We run more than 35,000 experiments with 16-bit inputs and k-bit parameters to examine which zero-shot quantization methods improve scaling for 3 to 8-bit precision at scales of 19M to 176B parameters across the LLM families BLOOM, OPT, NeoX/Pythia, and GPT-2. We find that it is challenging to improve the bit-level scaling trade-off, with the only improvements being the use of a small block size -- splitting the parameters into small independently quantized blocks -- and the quantization data type being used (e.g., Int vs Float). Overall, our findings show that 4-bit precision is almost universally optimal for total model bits and zero-shot accuracy.

To optimally coordinate with others in cooperative games, it is often crucial to have information about one’s collaborators: successful driving requires understanding which side of the road to drive on. However, not every feature of collaborators is strategically relevant: the fine-grained acceleration of drivers may be ignored while maintaining optimal coordination. We show that there is a well-defined dichotomy between strategically relevant and irrelevant information. Moreover, we show that, in dynamic games, this dichotomy has a compact representation that can be efficiently computed via a Bellman backup operator. We apply this algorithm to analyze the strategically relevant information for tasks in both a standard and a partially observable version of the Overcooked environment. Theoretical and empirical results show that our algorithms are significantly more efficient than baselines. Videos are available at https://minknowledge.github.io.

Mixup, a simple data augmentation method that randomly mixes two data points via linear interpolation, has been extensively applied in various deep learning applications to gain better generalization. However, its theoretical explanation remains largely unclear. In this work, we aim to seek a fundamental understanding of the benefits of Mixup. We first show that Mixup using different linear interpolation parameters for features and labels can still achieve similar performance as standard Mixup. This indicates that the intuitive linearity explanation in Zhang et al., (2018) may not fully explain the success of Mixup. Then, we perform a theoretical study of Mixup from the feature learning perspective. We consider a feature-noise data model and show that Mixup training can effectively learn the rare features (appearing in a small fraction of data) from its mixture with the common features (appearing in a large fraction of data). In contrast, standard training can only learn the common features but fails to learn the rare features, thus suffering from bad generalization performance. Moreover, our theoretical analysis also shows that the benefits of Mixup for feature learning are mostly gained in the early training phase, based on which we propose to apply early stopping in Mixup. Experimental results verify our theoretical findings and demonstrate the effectiveness of the early-stopped Mixup training.

Mediation analysis learns the causal effect transmitted via mediator variables between treatments and outcomes, and receives increasing attention in various scientific domains to elucidate causal relations. Most existing works focus on point-exposure studies where each subject only receives one treatment at a single time point. However, there are a number of applications (e.g., mobile health) where the treatments are sequentially assigned over time and the dynamic mediation effects are of primary interest. Proposing a reinforcement learning (RL) framework, we are the first to evaluate dynamic mediation effects in settings with infinite horizons. We decompose the average treatment effect into an immediate direct effect, an immediate mediation effect, a delayed direct effect, and a delayed mediation effect. Upon the identification of each effect component, we further develop robust and semi-parametrically efficient estimators under the RL framework to infer these causal effects. The superior performance of the proposed method is demonstrated through extensive numerical studies, theoretical results, and an analysis of a mobile health dataset. A Python implementation of the proposed procedure is available at https://github.com/linlinlin97/MediationRL.

The estimation of repeatedly nested expectations is a challenging task that arises in many real-world systems. However, existing methods generally suffer from high computational costs when the number of nestings becomes large. Fix any non-negative integer $D$ for the total number of nestings. Standard Monte Carlo methods typically cost at least $\mathcal{O}(\varepsilon^{-(2+D)})$ and sometimes $\mathcal {O}(\varepsilon^{-2(1+D)})$ to obtain an estimator up to $\varepsilon$-error. More advanced methods, such as multilevel Monte Carlo, currently only exist for $D = 1$. In this paper, we propose a novel Monte Carlo estimator called $\mathsf{READ}$, which stands for ``Recursive Estimator for Arbitrary Depth.'' Our estimator has an optimal computational cost of $\mathcal{O}(\varepsilon^{-2})$ for every fixed $D$ under suitable assumptions, and a nearly optimal computational cost of $\mathcal{O}(\varepsilon^{-2(1 + \delta)})$ for any $0 < \delta < \frac12$ under much more general assumptions. Our estimator is also unbiased, which makes it easy to parallelize. The key ingredients in our construction are an observation of the problem's recursive structure and the recursive use of the randomized multilevel Monte Carlo method.

We introduce EM-Network, a novel self-distillation approach that effectively leverages target information for supervised sequence-to-sequence (seq2seq) learning. In contrast to conventional methods, it is trained with oracle guidance, which is derived from the target sequence. Since the oracle guidance compactly represents the target-side context that can assist the sequence model in solving the task, the EM-Network achieves a better prediction compared to using only the source input. To allow the sequence model to inherit the promising capability of the EM-Network, we propose a new self-distillation strategy, where the original sequence model can benefit from the knowledge of the EM-Network in a one-stage manner. We conduct comprehensive experiments on two types of seq2seq models: connectionist temporal classification (CTC) for speech recognition and attention-based encoder-decoder (AED) for machine translation. Experimental results demonstrate that the EM-Network significantly advances the current state-of-the-art approaches, improving over the best prior work on speech recognition and establishing state-of-the-art performance on WMT'14 and IWSLT'14.

Supervised learning models have been used in various domains such as lending, college admission, face recognition, natural language processing, etc. However, they may inherit pre-existing biases from training data and exhibit discrimination against protected social groups. Various fairness notions have been proposed to address unfairness issues. In this work, we focus on Equalized Loss (EL), a fairness notion that requires the expected loss to be (approximately) equalized across different groups. Imposing EL on the learning process leads to a non-convex optimization problem even if the loss function is convex, and the existing fair learning algorithms cannot properly be adopted to find the fair predictor under the EL constraint. This paper introduces an algorithm that can leverage off-the-shelf convex programming tools (e.g., CVXPY (Diamond and Boyd, 2016; Agrawal et al., 2018)) to efficiently find the global optimum of this non-convex optimization. In particular, we propose the ELminimizer algorithm, which finds the optimal fair predictor under EL by reducing the non-convex optimization to a sequence of convex optimization problems. We theoretically prove that our algorithm finds the global optimal solution under certain conditions. Then, we support our theoretical results through several empirical studies