ICLR 2023 论文列表

Meta-learning tries to leverage information from similar learning tasks. In the commonly-used bilevel optimization formulation, the shared parameter is learned in the outer loop by minimizing the average loss over all tasks. However, the converged solution may be comprised in that it only focuses on optimizing on a small subset of tasks. To alleviate this problem, we consider meta-learning as a multi-objective optimization (MOO) problem, in which each task is an objective. However, existing MOO solvers need to access all the objectives’ gradients in each iteration, and cannot scale to the huge number of tasks in typical meta-learning settings. To alleviate this problem, we propose a scalable gradient-based solver with the use of mini-batch. We provide theoretical guarantees on the Pareto optimality or Pareto stationarity of the converged solution. Empirical studies on various machine learning settings demonstrate that the proposed method is efficient, and achieves better performance than the baselines, particularly on improving the performance of the poorly-performing tasks and thus alleviating the compromising phenomenon.

We investigate the problem of transferring an expert policy from a source robot to multiple different robots. To solve this problem, we propose a method name Meta-Evolve that uses continuous robot evolution to efficiently transfer the policy to a newly defined meta robot and then to each target robot. Since the meta robot is closer to the target robots, our approach can significantly naive one-to-one policy transfer. We also present three heuristic approaches with theoretical results to determine the meta robot. Experiments have shown that with three target robots, our method is able to improve over the baseline of launching multiple independent one-to-one robot-to-robot policy transfers by up to 2.4$\times$ in terms of training and exploration needed.

We study the task of training regression models with the guarantee of _label_ differential privacy (DP). Based on a global prior distribution of label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a "randomized response on bins", and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm.

Lighter and faster image restoration (IR) models are crucial for the deployment on resource-limited devices. Binary neural network (BNN), one of the most promising model compression methods, can dramatically reduce the computations and parameters of full-precision convolutional neural networks (CNN). However, there are different properties between BNN and full-precision CNN, and we can hardly use the experience of designing CNN to develop BNN. In this study, we reconsider components in binary convolution, such as residual connection, BatchNorm, activation function, and structure, for IR tasks. We conduct systematic analyses to explain each component's role in binary convolution and discuss the pitfalls. Specifically, we find that residual connection can reduce the information loss caused by binarization; BatchNorm can solve the value range gap between residual connection and binary convolution; The position of the activation function dramatically affects the performance of BNN. Based on our findings and analyses, we design a simple yet efficient basic binary convolution unit (BBCU). Furthermore, we divide IR networks into four parts and specially design variants of BBCU for each part to explore the benefit of binarizing these parts. We conduct experiments on different IR tasks, and our BBCU significantly outperforms other BNNs and lightweight models, which shows that BBCU can serve as a basic unit for binarized IR networks. All codes and models will be released.

One-shot non-autoregressive neural networks, different from RL-based ones, have been actively adopted for solving combinatorial optimization (CO) problems, which can be trained by the objective score in a self-supervised manner. Such methods have shown their superiority in efficiency (e.g. by parallelization) and potential for tackling predictive CO problems for decision-making under uncertainty. While the discrete constraints often become a bottleneck for gradient-based neural solvers, as currently handled in three typical ways: 1) adding a soft penalty in the objective, where a bounded violation of the constraints cannot be guaranteed, being critical to many constraint-sensitive scenarios; 2) perturbing the input to generate an approximate gradient in a black-box manner, though the constraints are exactly obeyed while the approximate gradients can hurt the performance on the objective score; 3) a compromise by developing soft algorithms whereby the output of neural networks obeys a relaxed constraint, and there can still occur an arbitrary degree of constraint-violation. Towards the ultimate goal of establishing a general framework for neural CO solver with the ability to control an arbitrary-small degree of constraint violation, in this paper, we focus on a more achievable and common setting: the cardinality constraints, which in fact can be readily encoded by a differentiable optimal transport (OT) layer. Based on this observation, we propose OT-based cardinality constraint encoding for end-to-end CO problem learning with two variants: Sinkhorn and Gumbel-Sinkhorn, whereby their violation of the constraints can be exactly characterized and bounded by our theoretical results. On synthetic and real-world CO problem instances, our methods surpass the state-of-the-art CO network and are comparable to (if not superior to) the commercial solver Gurobi. In particular, we further showcase a case study of applying our approach to the predictive portfolio optimization task on real-world asset price data, improving the Sharpe ratio from 1.1 to 2.0 of a strong LSTM+Gurobi baseline under the classic predict-then-optimize paradigm.

Many works show that node-level predictions of Graph Neural Networks (GNNs) are unrobust to small, often termed adversarial, changes to the graph structure. However, because manual inspection of a graph is difficult, it is unclear if the studied perturbations always preserve a core assumption of adversarial examples: that of unchanged semantic content. To address this problem, we introduce a more principled notion of an adversarial graph, which is aware of semantic content change. Using Contextual Stochastic Block Models (CSBMs) and real-world graphs, our results suggest: $i)$ for a majority of nodes the prevalent perturbation models include a large fraction of perturbed graphs violating the unchanged semantics assumption; $ii)$ surprisingly, all assessed GNNs show over-robustness - that is robustness beyond the point of semantic change. We find this to be a complementary phenomenon to adversarial examples and show that including the label-structure of the training graph into the inference process of GNNs significantly reduces over-robustness, while having a positive effect on test accuracy and adversarial robustness. Theoretically, leveraging our new semantics-aware notion of robustness, we prove that there is no robustness-accuracy tradeoff for inductively classifying a newly added node.

Neural Radiance Fields (NeRFs) aim to synthesize novel views of objects and scenes, given the object-centric camera views with large overlaps. However, we conjugate that this paradigm does not fit the nature of the street views that are collected by many self-driving cars from the large-scale unbounded scenes. Also, the onboard cameras perceive scenes without much overlapping. Thus, existing NeRFs often produce blurs, "floaters" and other artifacts on street-view synthesis. In this paper, we propose a new street-view NeRF (S-NeRF) that considers novel view synthesis of both the large-scale background scenes and the foreground moving vehicles jointly. Specifically, we improve the scene parameterization function and the camera poses for learning better neural representations from street views. We also use the the noisy and sparse LiDAR points to boost the training and learn a robust geometry and reprojection based confidence to address the depth outliers. Moreover, we extend our S-NeRF for reconstructing moving vehicles that is impracticable for conventional NeRFs. Thorough experiments on the large-scale driving datasets (e.g., nuScenes and Waymo) demonstrate that our method beats the state-of-the-art rivals by reducing 7～40% of the mean-squared error in the street-view synthesis and a 45% PSNR gain for the moving vehicles rendering.

We consider the classical version of the optimal partial transport problem. Let $\mu$ (with a mass of $U$) and $\nu$ (with a mass of $S$) be two discrete mass distributions with $S \le U$ and let $n$ be the total number of points in the supports of $\mu$ and $\nu$. For a parameter $\alpha \in [0,S]$, consider the minimum-cost transport plan $\sigma_\alpha$ that transports a mass of $\alpha$ from $\nu$ to $\mu$. An \emph{OT-profile} captures the behavior of the cost of $\sigma_\alpha$ as $\alpha$ varies from $0$ to $S$. There is only limited work on OT-profile and its mathematical properties (see~\cite{figalli2010optimal}). In this paper, we present a novel framework to analyze the properties of the OT-profile and also present an algorithm to compute it. When $\mu$ and $\nu$ are discrete mass distributions, we show that the OT-profile is a piecewise-linear non-decreasing convex function. Let $K$ be the combinatorial complexity of this function, i.e., the number of line segments required to represent the OT-profile. Our exact algorithm computes the OT-profile in $\tilde{O}(n^2K)$ time. Given $\delta > 0$, we also show that the algorithm by ~\cite{lahn2019graph} can be used to $\delta$-approximate the OT-profile in $O(n^2/\delta + n/\delta^2)$ time. This approximation is a piecewise-linear function of a combinatorial complexity of $O(1/\delta)$. An OT-profile is arguably more valuable than the OT-cost itself and can be used within applications. Under a reasonable assumption of outliers, we also show that the first derivative of the OT-profile sees a noticeable rise before any of the mass from outliers is transported. By using this property, we get an improved prediction accuracy for an outlier detection experiment. We also use this property to predict labels and estimate the class priors within PU-Learning experiments. Both these experiments are conducted on real datasets.

We improve upon previous oblivious sketching and turnstile streaming results for $\ell_1$ and logistic regression, giving a much smaller sketching dimension achieving $O(1)$-approximation and yielding an efficient optimization problem in the sketch space. Namely, we achieve for any constant $c>0$ a sketching dimension of $\tilde{O}(d^{1+c})$ for $\ell_1$ regression and $\tilde{O}(\mu d^{1+c})$ for logistic regression, where $\mu$ is a standard measure that captures the complexity of compressing the data. For $\ell_1$-regression our sketching dimension is near-linear and improves previous work which either required $\Omega(\log d)$-approximation with this sketching dimension, or required a larger $\operatorname{poly}(d)$ number of rows. Similarly, for logistic regression previous work had worse $\operatorname{poly}(\mu d)$ factors in its sketching dimension. We also give a tradeoff that yields a $1+\varepsilon$ approximation in input sparsity time by increasing the total size to $(d\log(n)/\varepsilon)^{O(1/\varepsilon)}$ for $\ell_1$ and to $(\mu d\log(n)/\varepsilon)^{O(1/\varepsilon)}$ for logistic regression. Finally, we show that our sketch can be extended to approximate a regularized version of logistic regression where the data-dependent regularizer corresponds to the variance of the individual logistic losses.

We prove that image classifiers are fundamentally sensitive to small perturbations in their inputs. Specifically, we show that given some image space of $n$-by-$n$ images, all but a tiny fraction of images in any image class induced over that space can be moved outside that class by adding some perturbation whose $p$-norm is $O(n^{1/\max{(p,1)}})$, as long as that image class takes up at most half of the image space. We then show that $O(n^{1/\max{(p,1)}})$ is asymptotically optimal. Finally, we show that an increase in the bit depth of the image space leads to a loss in robustness. We supplement our results with a discussion of their implications for vision systems.

Large pre-trained models exhibit distinct and complementary capabilities dependent on the data they are trained on. Language models such as GPT-3 are capable of textual reasoning but cannot understand visual information, while vision models such as DALL-E can generate photorealistic photos but fail to understand complex language descriptions. In this work, we propose a unified framework for composing ensembles of different pre-trained models -- combining the strengths of each individual model to solve various multimodal problems in a zero-shot manner. We use pre-trained models as "generators" or "scorers" and compose them via closed-loop iterative consensus optimization. The generator constructs proposals and the scorers iteratively provide feedback to refine the generated result. Such closed-loop communication enables models to correct errors caused by other models, significantly boosting performance on downstream tasks, e.g. improving accuracy on grade school math problems by 7.5%, without requiring any model finetuning. We demonstrate that consensus achieved by an ensemble of scorers outperforms the feedback of a single scorer, by leveraging the strengths of each expert model. Results show that the proposed method can be used as a general purpose framework for a wide range of zero-shot multimodal tasks, such as image generation, video question answering, mathematical reasoning, and robotic manipulation.

We introduce Noise Injection Node Regularization (NINR), a method of injecting structured noise into Deep Neural Networks (DNN) during the training stage, resulting in an emergent regularizing effect. We present theoretical and empirical evidence for substantial improvement in robustness against various test data perturbations for feed-forward DNNs when trained under NINR. The novelty in our approach comes from the interplay of adaptive noise injection and initialization conditions such that noise is the dominant driver of dynamics at the start of training. As it simply requires the addition of external nodes without altering the existing network structure or optimization algorithms, this method can be easily incorporated into many standard problem specifications. We find improved stability against a number of data perturbations, including domain shifts, with the most dramatic improvement obtained for unstructured noise, where our technique outperforms other existing methods such as dropout or $L_2$ regularization, in some cases. We further show that desirable generalization properties on clean data are generally maintained.

Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other retrieval tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, this overlooks the fact that there are many diverse and unique retrieval problems, each targeting different search intents, queries, and search domains. In this paper, we suggest to work on Few-shot Dense Retrieval, a setting where each task comes with a short description and a few examples. To address this, we introduce Prompt-based Query Generation forRetrieval (Promptagator): for each task, we feed the few-shot examples to a large language model (LLM) and prompt it to behave as a task-specific query generator. Using this, we can synthetically generate a large number of relevant queries for any document, yielding abundant data for training task-specific retrievers --- with no reliance on traditional resources such as Natural Questions (Kwiatkowskiet al., 2019) or MS MARCO (Nguyen et al., 2016). Surprisingly, Promptagator with only 8 annotated examples enables efficient dual encoder retrievers to outperform computationally more expensive models trained on MS MARCO such as ColBERT v2 (Santhanam et al., 2022) by more than 1.2 points nDCG@10 on average on 11 retrieval sets. Further training standard-size re-rankers using the same generated data yields another 5.0 points nDCG@10 improvement. Our studies show that synthetic query generation can be far more effective than previously observed, especially when a small amount of task-specific knowledge is given.

Boundary conditions (BCs) are important groups of physics-enforced constraints that are necessary for solutions of Partial Differential Equations (PDEs) to satisfy at specific spatial locations. These constraints carry important physical meaning, and guarantee the existence and the uniqueness of the PDE solution. Current neural-network based approaches that aim to solve PDEs rely only on training data to help the model learn BCs implicitly, however, there is no guarantee of BC satisfaction by these models during evaluation. In this work, we propose Boundary enforcing Operator Network (BOON) that enables the BC satisfaction of neural operators by making structural changes to the operator kernel. We provide our refinement procedure, and demonstrate the satisfaction of physics-based BCs such as Dirichlet, Neumann, and periodic by the solutions obtained by BOON. Numerical experiments based on multiple PDEs with a wide variety of applications indicate that the proposed approach ensures satisfaction of BCs, and leads to more accurate solutions over the whole domain. The proposed method exhibits a (2X-20X) improvement in accuracy (0.000084 relative $L^2$ error for Burgers' equation). Code available at: https://github.com/amazon-science/boon.

Although machine learning algorithms have achieved state-of-the-art status in image classification, recent studies have substantiated that the ability of the models to learn several tasks in sequence, termed continual learning (CL), often suffers from abrupt degradation of performance from previous tasks. A large body of CL frameworks has been devoted to alleviating this issue. However, we observe that forgetting phenomena in CL are not always unfavorable, especially when there is bias (spurious correlation) in training data. We term such type of forgetting benign forgetting, and categorize detrimental forgetting as malignant forgetting. Based on this finding, our objective in this study is twofold: (a) to discourage malignant forgetting by generating previous representations, and (b) encourage benign forgetting by employing contrastive learning in conjunction with feature-level augmentation. Extensive evaluations of biased experimental setups demonstrate that our proposed method, Learning without Prejudices, is effective for continual unbiased learning.

In this paper, we introduce the notion of replicable policies in the context of stochastic bandits, one of the canonical problems in interactive learning. A policy in the bandit environment is called replicable if it pulls, with high probability, the exact same sequence of arms in two different and independent executions (i.e., under independent reward realizations). We show that not only do replicable policies exist, but also they achieve almost the same optimal (non-replicable) regret bounds in terms of the time horizon. More specifically, in the stochastic multi-armed bandits setting, we develop a policy with an optimal problem-dependent regret bound whose dependence on the replicability parameter is also optimal. Similarly, for stochastic linear bandits (with finitely and infinitely many arms) we develop replicable policies that achieve the best-known problem-independent regret bounds with an optimal dependency on the replicability parameter. Our results show that even though randomization is crucial for the exploration-exploitation trade-off, an optimal balance can still be achieved while pulling the exact same arms in two different rounds of executions.

Recent works have revealed the superiority of feature-level fusion for cross-modal 3D object detection, where fine-grained feature propagation from 2D image pixels to 3D LiDAR points has been widely adopted for performance improvement. Still, the potential of heterogeneous feature propagation between 2D and 3D domains has not been fully explored. In this paper, in contrast to existing pixel-to-point feature propagation, we investigate an opposite point-to-pixel direction, allowing point-wise features to flow inversely into the 2D image branch. Thus, when jointly optimizing the 2D and 3D streams, the gradients back-propagated from the 2D image branch can boost the representation ability of the 3D back-bone network working on LiDAR point clouds. Then, combining pixel-to-point and point-to-pixel information flow mechanisms, we further construct an interactive bidirectional feature propagation framework, dubbed BiProDet. In addition to the architectural design, we also propose normalized local coordinates map estimation, a new 2D auxiliary task for the training of the 2D image branch, which facilitates learning local spatial-aware features from the image modality and implicitly enhances the overall 3D detection performance. Extensive experiments and ablation studies validate the effectiveness of our method. Notably, we rank 1st on the highly competitive KITTI benchmark on the cyclist class by the time of submission. We also uploaded the source code in the supplementary material, which will be publicly available.

In the era of deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually different. Although there exist many different designs for finetuning, a full understanding of when and why these algorithms work has been elusive. We analyze how the choice of task head controls feature adaptation and hence influences the downstream performance. By decomposing the feature's learning dynamics, we find the key aspect is the training accuracy and loss at the beginning of finetuning, which determines the "energy" available for the feature's adaptation. We identify a significant trend in the effect of changes in this initial energy on the resulting features after finetuning. Specifically, as the energy increases, the Euclidean and cosine distances between the resulting and original features increase, while their dot product (and the resulting features’ norm) first increases and then decreases. Inspired by this, we give several practical principles that lead to better downstream performance. We analytically prove this trend in an overparamterized linear setting and verify its applicability to different experimental settings.

Time series classification is an important problem in the real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributions. In this paper, we propose to view time series classification from the distribution perspective. We argue that the temporal complexity of a time series dataset could attribute to unknown latent distributions that need characterize. To this end, we propose DIVERSIFY for out-of-distribution (OOD) representation learning on dynamic distributions of times series. DIVERSIFY takes an iterative process: it first obtains the ‘worst-case’ latent distribution scenario via adversarial training, then reduces the gap between these latent distributions. We then show that such an algorithm is theoretically supported. Extensive experiments are conducted on seven datasets with different OOD settings across gesture recognition, speech commands recognition, wearable stress and affect detection, and sensor-based human activity recognition. Qualitative and quantitative results demonstrate that DIVERSIFY significantly outperforms other baselines and effectively characterizes the latent distributions. Code is available at https://github.com/microsoft/robustlearn.