NeurIPS 2023 论文列表

A recent line of work in high-dimensional statistics working under the Gaussian mixture hypothesis has led to a number of results in the context of empirical risk minimization, Bayesian uncertainty quantification, separation of kernel methods and neural networks, ensembling and fluctuation of random features. We provide rigorous proofs for the applicability of these results to a general class of datasets $(\mathbf{x_i},y_i, {i=1,\dots,n})$ containing independent samples from a mixture distribution $\sum_{c\in\mathcal{C}} \rho_{c}P_{c}^{\mathbf{x}}$. Specifically, we consider the hypothesis class of generalized linear models $\hat{y} = F(\mathbf{\Theta}^{\top}\mathbf{x})$ and investigate the asymptotic joint statistics of a family of generalized linear estimators $(\mathbf{\Theta}^{(1)}, \dots, \mathbf{\Theta}^{(M)})$, obtained either from (a) minimizing an empirical risk $\hat{R_n}^{(m)}(\mathbf{\Theta}^{(m)};\mathbf{X},\mathbf{y})$ or (b) sampling from the associated Gibbs measure $\exp(-\beta n \hat{R_n}^{(m)}(\mathbf{\Theta}^{(m)};\mathbf{X},\mathbf{y}))$. Our main contribution is to characterize under which conditions the asymptotic joint statistics of this family depends (on a weak sense) only on the means and covariances of the class conditional features distribution $P_{c}^{\mathbf{x}}$. This allows us to prove the universality of different quantities of interest, including training, generalization errors, as well as the geometrical properties and correlations of the estimators.

``Effective robustness'' measures the extra out-of-distribution (OOD) robustness beyond what can be predicted from the in-distribution (ID) performance. Existing effective robustness evaluations typically use a single test set such as ImageNet to evaluate the ID accuracy. This becomes problematic when evaluating models trained on different data distributions, e.g., comparing models trained on ImageNet vs. zero-shot language-image pre-trained models trained on LAION. In this paper, we propose a new evaluation metric to evaluate and compare the effective robustness of models trained on different data. To do this, we control for the accuracy on multiple ID test sets that cover the training distributions for all the evaluated models. Our new evaluation metric provides a better estimate of effective robustness when there are models with different training data. It may also explain the surprising effective robustness gains of zero-shot CLIP-like models exhibited in prior works that used ImageNet as the only ID test set, while the gains diminish under our new evaluation. Additional artifacts including interactive visualizations are provided at https://shizhouxing.github.io/effective-robustness.

Recent advances in attention-free sequence models rely on convolutions as alternatives to the attention operator at the core of Transformers. In particular, long convolution sequence models have achieved state-of-the-art performance in many domains, but incur a significant cost during auto-regressive inference workloads -- naively requiring a full pass (or caching of activations) over the input sequence for each generated token -- similarly to attention-based models. In this paper, we seek to enable $\mathcal O(1)$ compute and memory cost per token in any pre-trained long convolution architecture to reduce memory footprint and increase throughput during generation. Concretely, our methods consist in extracting low-dimensional linear state-space models from each convolution layer, building upon rational interpolation and model-order reduction techniques. We further introduce architectural improvements to convolution-based layers such as Hyena: by weight-tying the filters across channels into heads, we achieve higher pre-training quality and reduce the number of filters to be distilled. The resulting model achieves 10x higher throughput than Transformers and 1.5x higher than Hyena at 1.3B parameters, without any loss in quality after distillation.

Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments. However, existing benchmarks tend to oversimplify the scene by solely focusing on lane perception tasks. Observing that human drivers rely on both lanes and traffic signals to operate their vehicles safely, we present OpenLane-V2, the first dataset on topology reasoning for traffic scene structure. The objective of the presented dataset is to advance research in understanding the structure of road scenes by examining the relationship between perceived entities, such as traffic elements and lanes. Leveraging existing datasets, OpenLane-V2 consists of 2,000 annotated road scenes that describe traffic elements and their correlation to the lanes. It comprises three primary sub-tasks, including the 3D lane detection inherited from OpenLane, accompanied by corresponding metrics to evaluate the model’s performance. We evaluate various state-of-the-art methods, and present their quantitative and qualitative results on OpenLane-V2 to indicate future avenues for investigating topology reasoning in traffic scenes.

Over the last several years, there has been significant progress in developing neural solvers for the Schrödinger Bridge (SB) problem and applying them to generative modelling. This new research field is justifiably fruitful as it is interconnected with the practically well-performing diffusion models and theoretically grounded entropic optimal transport (EOT). Still, the area lacks non-trivial tests allowing a researcher to understand how well the methods solve SB or its equivalent continuous EOT problem. We fill this gap and propose a novel way to create pairs of probability distributions for which the ground truth OT solution is known by the construction. Our methodology is generic and works for a wide range of OT formulations, in particular, it covers the EOT which is equivalent to SB (the main interest of our study). This development allows us to create continuous benchmark distributions with the known EOT and SB solutions on high-dimensional spaces such as spaces of images. As an illustration, we use these benchmark pairs to test how well existing neural EOT/SB solvers actually compute the EOT solution. Our code for constructing benchmark pairs under different setups is available at: https://github.com/ngushchin/EntropicOTBenchmark

Chain-of-thought prompting (CoT) and tool augmentation have been validated in recent work as effective practices for improving large language models (LLMs) to perform step-by-step reasoning on complex math-related tasks. However, most existing math reasoning datasets may not be able to fully evaluate and analyze the ability of LLMs in manipulating tools and performing reasoning, as they often only require very few invocations of tools or miss annotations for evaluating intermediate reasoning steps, thus supporting only outcome evaluation. To address the issue, we construct **CARP**, a new Chinese dataset consisting of 4,886 computation-intensive algebra problems with formulated annotations on intermediate steps, facilitating the evaluation of the intermediate reasoning process. In CARP, we test four LLMs with CoT prompting, and find that they are all prone to make mistakes at the early steps of the solution, leading to incorrect answers. Based on this finding, we propose a new approach that can facilitate the deliberation on reasoning steps with tool interfaces, namely **DELI**. In DELI, we first initialize a step-by-step solution based on retrieved exemplars, then iterate two deliberation procedures that check and refine the intermediate steps of the generated solution, from both tool manipulation and natural language reasoning perspectives, until solutions converge or the maximum iteration is achieved. Experimental results on CARP and six other datasets show that the proposed DELI mostly outperforms competitive baselines, and can further boost the performance of existing CoT methods. Our data and code are available at https://github.com/RUCAIBox/CARP.

Best Arm Identification (BAI) problems are progressively used for data-sensitive applications, such as designing adaptive clinical trials, tuning hyper-parameters, and conducting user studies to name a few. Motivated by the data privacy concerns invoked by these applications, we study the problem of BAI with fixed confidence under $\epsilon$-global Differential Privacy (DP). First, to quantify the cost of privacy, we derive a lower bound on the sample complexity of any $\delta$-correct BAI algorithm satisfying $\epsilon$-global DP. Our lower bound suggests the existence of two privacy regimes depending on the privacy budget $\epsilon$. In the high-privacy regime (small $\epsilon$), the hardness depends on a coupled effect of privacy and a novel information-theoretic quantity, called the Total Variation Characteristic Time. In the low-privacy regime (large $\epsilon$), the sample complexity lower bound reduces to the classical non-private lower bound. Second, we propose AdaP-TT, an $\epsilon$-global DP variant of the Top Two algorithm. AdaP-TT runs in *arm-dependent adaptive episodes* and adds *Laplace noise* to ensure a good privacy-utility trade-off. We derive an asymptotic upper bound on the sample complexity of AdaP-TT that matches with the lower bound up to multiplicative constants in the high-privacy regime. Finally, we provide an experimental analysis of AdaP-TT that validates our theoretical results.

Molecular Property Prediction (MPP) is a crucial task in the AI-driven Drug Discovery (AIDD) pipeline, which has recently gained considerable attention thanks to advancements in deep learning. However, recent research has revealed that deep models struggle to beat traditional non-deep ones on MPP. In this study, we benchmark 12 representative models (3 non-deep models and 9 deep models) on 15 molecule datasets. Through the most comprehensive study to date, we make the following key observations: \textbf{(\romannumeral 1)} Deep models are generally unable to outperform non-deep ones; \textbf{(\romannumeral 2)} The failure of deep models on MPP cannot be solely attributed to the small size of molecular datasets; \textbf{(\romannumeral 3)} In particular, some traditional models including XGB and RF that use molecular fingerprints as inputs tend to perform better than other competitors. Furthermore, we conduct extensive empirical investigations into the unique patterns of molecule data and inductive biases of various models underlying these phenomena. These findings stimulate us to develop a simple-yet-effective feature mapping method for molecule data prior to feeding them into deep models. Empirically, deep models equipped with this mapping method can beat non-deep ones in most MoleculeNet datasets. Notably, the effectiveness is further corroborated by extensive experiments on cutting-edge dataset related to COVID-19 and activity cliff datasets.

Graph-based Collaborative Filtering (GCF) is widely used in personalized recommendation systems. However, GCF suffers from a fundamental problem where features tend to occupy the embedding space inefficiently (by spanning only a low-dimensional subspace). Such an effect is characterized in GCF by the embedding space being dominated by a few of popular items with the user embeddings highly concentrated around them. This enhances the so-called Matthew effect of the popularity bias where popular items are highly recommend whereas remaining items are ignored. In this paper, we analyze the above effect in GCF and reveal that the simplified graph convolution operation (typically used in GCF) shrinks the singular space of the feature matrix. As typical approaches (i.e., optimizing the uniformity term) fail to prevent the embedding space degradation, we propose a decorrelation-enhanced GCF objective that promotes feature diversity by leveraging the so-called principle of redundancy reduction in embeddings. However, unlike conventional methods that use the Euclidean geometry to relax hard constraints for decorrelation, we exploit non-Euclidean geometry. Such a choice helps maintain the range space of the matrix and obtain small condition number, which prevents the embedding space degradation. Our method outperforms contrastive-based GCF models on several benchmark datasets and improves the performance for unpopular items.

We investigate how shallow ReLU networks interpolate between known regions. Our analysis shows that empirical risk minimizers converge to a minimum norm interpolant as the number of data points and parameters tends to infinity when a weight decay regularizer is penalized with a coefficient which vanishes at a precise rate as the network width and the number of data points grow. With and without explicit regularization, we numerically study the implicit bias of common optimization algorithms towards known minimum norm interpolants.

Exact inference of marginals in probabilistic graphical models (PGM) is known to be intractable, necessitating the use of approximate methods. Most of the existing variational techniques perform iterative message passing in loopy graphs which is slow to converge for many benchmarks. In this paper, we propose a new algorithm for marginal inference that is based on the incremental build-infer-approximate (IBIA) paradigm. Our algorithm converts the PGM into a sequence of linked clique tree forests (SLCTF) with bounded clique sizes, and then uses a heuristic belief update algorithm to infer the marginals. For the special case of Bayesian networks, we show that if the incremental build step in IBIA uses the topological order of variables then (a) the prior marginals are consistent in all CTFs in the SLCTF and (b) the posterior marginals are consistent once all evidence variables are added to the SLCTF. In our approach, the belief propagation step is non-iterative and the accuracy-complexity trade-off is controlled using user-defined clique size bounds. Results for several benchmark sets from recent UAI competitions show that our method gives either better or comparable accuracy than existing variational and sampling based methods, with smaller runtimes.

Recent years have witnessed increasing attentions on two-sample test with diverse real applications, while this work takes one more step on the exploration of local significant differences for two-sample test. We propose the ME$_\text{MaBiD}$, an effective test for two-sample testing, and the basic idea is to exploit local information by multiple Mahalanobis kernels and introduce bi-directional hypothesis for testing. On the exploration of local significant differences, we first partition the embedding space into several rectangle regions via a new splitting criterion, which is relevant to test power and data correlation. We then explore local significant differences based on our bi-directional masked $p$-value together with the ME$_\text{MaBiD}$ test. Theoretically, we present the asymptotic distribution and lower bounds of test power for our ME$_\text{MaBiD}$ test, and control the familywise error rate on the exploration of local significant differences. We finally conduct extensive experiments to validate the effectiveness of our proposed methods on two-sample test and the exploration of local significant differences.

We consider the problem of mixed linear regression (MLR), where each observed sample belongs to one of $K$ unknown linear models. In practical applications, the mixture of the $K$ models may be imbalanced with a significantly different number of samples from each model. Unfortunately, most MLR methods do not perform well in such settings. Motivated by this practical challenge, in this work we propose Mix-IRLS, a novel, simple and fast algorithm for MLR with excellent performance on both balanced and imbalanced mixtures. In contrast to popular approaches that recover the $K$ models simultaneously, Mix-IRLS does it sequentially using tools from robust regression. Empirically, beyond imbalanced mixtures, Mix-IRLS succeeds in a broad range of additional settings where other methods fail, including small sample sizes, presence of outliers, and an unknown number of models $K$. Furthermore, Mix-IRLS outperforms competing methods on several real-world datasets, in some cases by a large margin. We complement our empirical results by deriving a recovery guarantee for Mix-IRLS, which highlights its advantage on imbalanced mixtures.

Given the intractably large size of the space of proofs, any model that is capable of general deductive reasoning must generalize to proofs of greater complexity. Recent studies have shown that large language models (LLMs) possess some abstract deductive reasoning ability given chain-of-thought prompts. However, they have primarily been tested on proofs using modus ponens or of a specific size, and from the same distribution as the in-context examples. To measure the general deductive reasoning ability of LLMs, we test on a broad set of deduction rules and measure their ability to generalize to more complex proofs from simpler demonstrations from multiple angles: depth-, width-, and compositional generalization. To facilitate systematic exploration, we construct a new synthetic and programmable reasoning dataset that enables control over deduction rules and proof complexity. Our experiments on four LLMs of various sizes and training objectives show that they are able to generalize to compositional proofs. However, they have difficulty generalizing to longer proofs, and they require explicit demonstrations to produce hypothetical subproofs, specifically in proof by cases and proof by contradiction.

We aim to deepen the theoretical understanding of Graph Neural Networks (GNNs) on large graphs, with a focus on their expressive power. Existing analyses relate this notion to the graph isomorphism problem, which is mostly relevant for graphs of small sizes, or studied graph classification or regression tasks, while prediction tasks on \emph{nodes} are far more relevant on large graphs. Recently, several works showed that, on very general random graphs models, GNNs converge to certains functions as the number of nodes grows. In this paper, we provide a more complete and intuitive description of the function space generated by equivariant GNNs for node-tasks, through general notions of convergence that encompass several previous examples. We emphasize the role of input node features, and study the impact of \emph{node Positional Encodings} (PEs), a recent line of work that has been shown to yield state-of-the-art results in practice. Through the study of several examples of PEs on large random graphs, we extend previously known universality results to significantly more general models. Our theoretical results hint at some normalization tricks, which is shown numerically to have a positive impact on GNN generalization on synthetic and real data. Our proofs contain new concentration inequalities of independent interest.

Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient space information to derive OOD scores neglecting the role of \textbf{most important parameters} of the pre-trained network over In-Distribution data. In this study, we propose a novel approach called GradOrth to facilitate OOD detection based on one intriguing observation that the important features to identify OOD data lie in the lower-rank subspace of in-distribution (ID) data. In particular, we identify OOD data by computing the norm of gradient projection on \textit{the subspaces considered \textbf{important} for the in-distribution data}. A large orthogonal projection value (i.e. a small projection value) indicates the sample as OOD as it captures a weak correlation of the in-distribution (ID) data. This simple yet effective method exhibits outstanding performance, showcasing a notable reduction in the average false positive rate at a 95\% true positive rate (FPR95) of up to 8\% when compared to the current state-of-the-art methods.

As the size of circuit designs continues to grow rapidly, artificial intelligence technologies are being extensively used in Electronic Design Automation (EDA) to assist with circuit design. Placement and routing are the most time-consuming parts of the physical design process, and how to quickly evaluate the placement has become a hot research topic. Prior works either transformed circuit designs into images using hand-crafted methods and then used Convolutional Neural Networks (CNN) to extract features, which are limited by the quality of the hand-crafted methods and could not achieve end-to-end training, or treated the circuit design as a graph structure and used Graph Neural Networks (GNN) to extract features, which require time-consuming preprocessing. In our work, we propose a novel perspective for circuit design by treating circuit components as point clouds and using Transformer-based point cloud perception methods to extract features from the circuit. This approach enables direct feature extraction from raw data without any preprocessing, allows for end-to-end training, and results in high performance. Experimental results show that our method achieves state-of-the-art performance in congestion prediction tasks on both the CircuitNet and ISPD2015 datasets, as well as in design rule check (DRC) violation prediction tasks on the CircuitNet dataset. Our method establishes a bridge between the relatively mature point cloud perception methods and the fast-developing EDA algorithms, enabling us to leverage more collective intelligence to solve this task. To facilitate the research of open EDA design, source codes and pre-trained models are released at https://github.com/hustvl/circuitformer.

In modern machine learning, inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. Formally, in this problem, one is given as input three matrices $Q, K, V \in [-B,B]^{n \times d}$, and the goal is to construct the matrix $\mathrm{Att}(Q,K,V) := \mathrm{diag}(A {\bf 1}_n)^{-1} A V \in \mathbb{R}^{n \times d}$, where $A = \exp(QK^\top/d)$ is the `attention matrix', and $\exp$ is applied entry-wise. Straightforward methods for this problem explicitly compute the $n \times n$ attention matrix $A$, and hence require time $\Omega(n^2)$ even when $d = n^{o(1)}$ is small. In this paper, we investigate whether faster algorithms are possible by \emph{implicitly} making use of the matrix $A$. We present two results, showing that there is a sharp transition at $B = \Theta(\sqrt{\log n})$. $\bullet$ If $d = O(\log n)$ and $B = o(\sqrt{\log n})$, there is an $n^{1+o(1)}$ time algorithm to approximate $\mathrm{Att}(Q,K,V)$ up to $1/\mathrm{poly}(n)$ additive error. $\bullet$ If $d = O(\log n)$ and $B = \Theta (\sqrt{\log n})$, assuming the Strong Exponential Time Hypothesis from fine-grained complexity theory, it is impossible to approximate $\mathrm{Att}(Q,K,V)$ up to $1/\mathrm{poly}(n)$ additive error in truly subquadratic time $n^{2 - \Omega(1)}$. This gives a theoretical explanation for the phenomenon observed in practice that attention computation is much more efficient when the input matrices have smaller entries.

In this work, we revisit the generalization error of stochastic mirror descent for quadratically bounded losses studied in Telgarsky (2022). Quadratically bounded losses is a broad class of loss functions, capturing both Lipschitz and smooth functions, for both regression and classification problems. We study the high probability generalization for this class of losses on linear predictors in both realizable and non-realizable cases when the data are sampled IID or from a Markov chain. The prior work relies on an intricate coupling argument between the iterates of the original problem and those projected onto a bounded domain. This approach enables blackbox application of concentration inequalities, but also leads to suboptimal guarantees due in part to the use of a union bound across all iterations. In this work, we depart significantly from the prior work of Telgarsky (2022), and introduce a novel approach for establishing high probability generalization guarantees. In contrast to the prior work, our work directly analyzes the moment generating function of a novel supermartingale sequence and leverages the structure of stochastic mirror descent. As a result, we obtain improved bounds in all aforementioned settings. Specifically, in the realizable case and non-realizable case with light-tailed sub-Gaussian data, we improve the bounds by a $\log T$ factor, matching the correct rates of $1/T$ and $1/\sqrt{T}$, respectively. In the more challenging case of heavy-tailed polynomial data, we improve the existing bound by a $\mathrm{poly}\ T$ factor.