ICML 2024 Papers

Many, if not most, systems of interest in science are naturally described as nonlinear dynamical systems. Empirically, we commonly access these systems through time series measurements. Often such time series may consist of discrete random variables rather than continuous measurements, or may be composed of measurements from multiple data modalities observed simultaneously. For instance, in neuroscience we may have behavioral labels in addition to spike counts and continuous physiological recordings. While by now there is a burgeoning literature on deep learning for dynamical systems reconstruction (DSR), multimodal data integration has hardly been considered in this context. Here we provide such an efficient and flexible algorithmic framework that rests on a multimodal variational autoencoder for generating a sparse teacher signal that guides training of a reconstruction model, exploiting recent advances in DSR training techniques. It enables to combine various sources of information for optimal reconstruction, even allows for reconstruction from symbolic data (class labels) alone, and connects different types of observations within a common latent dynamics space. In contrast to previous multimodal data integration techniques for scientific applications, our framework is fully generative, producing, after training, trajectories with the same geometrical and temporal structure as those of the ground truth system.

In-context learning (ICL) has emerged as a particularly remarkable characteristic of Large Language Models (LLM): given a pretrained LLM and an observed dataset, LLMs can make predictions for new data points from the same distribution without fine-tuning. Numerous works have postulated ICL as approximately Bayesian inference, rendering this a natural hypothesis. In this work, we analyse this hypothesis from a new angle through the *martingale property*, a fundamental requirement of a Bayesian learning system for exchangeable data. We show that the martingale property is a necessary condition for unambiguous predictions in such scenarios, and enables a principled, decomposed notion of uncertainty vital in trustworthy, safety-critical systems. We derive actionable checks with corresponding theory and test statistics which must hold if the martingale property is satisfied. We also examine if uncertainty in LLMs decreases as expected in Bayesian learning when more data is observed. In three experiments, we provide evidence for violations of the martingale property, and deviations from a Bayesian scaling behaviour of uncertainty, falsifying the hypothesis that ICL is Bayesian.

Lithography, transferring chip design masks to the silicon wafer, is the most important phase in modern semiconductor manufacturing flow. Due to the limitations of lithography systems, Extensive design optimizations are required to tackle the design and silicon mismatch. Inverse lithography technology (ILT) is one of the promising solutions to perform pre-fabrication optimization, termed mask optimization. Because of mask optimization problems’ constrained non-convexity, numerical ILT solvers rely heavily on good initialization to avoid getting stuck on sub-optimal solutions. Machine learning (ML) techniques are hence proposed to generate mask initialization for ILT solvers with one-shot inference, targeting faster and better convergence during ILT. This paper addresses the question of whether ML models can directly generate high-quality optimized masks without engaging ILT solvers in the loop. We propose an implicit learning ILT framework: ILILT, which leverages the implicit layer learning method and lithography-conditioned inputs to ground the model. Trained to understand the ILT optimization procedure, ILILT can outperform the state-of-the-art machine learning solutions, significantly improving efficiency and quality.

Active domain adaptation has shown promising results in enhancing unsupervised domain adaptation (DA), by actively selecting and annotating a small amount of unlabeled samples from the target domain. Despite its effectiveness in boosting overall performance, the gain usually concentrates on the categories that are readily improvable, while challenging categories that demand the utmost attention are often overlooked by existing models. To alleviate this discrepancy, we propose a novel category-aware active DA method that aims to boost the adaptation for the individual category without adversely affecting others. Specifically, our approach identifies the unlabeled data that are most important for the recognition of the targeted category. Our method assesses the impact of each unlabeled sample on the recognition loss of the target data via the influence function, which allows us to directly evaluate the sample importance, without relying on indirect measurements used by existing methods. Comprehensive experiments and in-depth explorations demonstrate the efficacy of our method on category-aware active DA over three datasets.

Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score based on contrasting two closely related language models is highly accurate at separating human-generated and machine-generated text. Based on this mechanism, we propose a novel LLM detector that only requires simple calculations using a pair of pre-trained LLMs. The method, called *Binoculars*, achieves state-of-the-art accuracy without any training data. It is capable of spotting machine text from a range of modern LLMs without any model-specific modifications. We comprehensively evaluate *Binoculars* on a number of text sources and in varied situations. Over a wide range of document types, *Binoculars* detects over 90% of generated samples from ChatGPT (and other LLMs) at a false positive rate of 0.01%, despite not being trained on any ChatGPT data. Code available at https://github.com/ahans30/Binoculars.

We present an algorithm for skill discovery from expert demonstrations. The algorithm first utilizes Large Language Models (LLMs) to propose an initial segmentation of the trajectories. Following that, a hierarchical variational inference framework incorporates the LLM-generated segmentation information to discover reusable skills by merging trajectory segments. To further control the trade-off between compression and reusability, we introduce a novel auxiliary objective based on the Minimum Description Length principle that helps guide this skill discovery process. Our results demonstrate that agents equipped with our method are able to discover skills that help accelerate learning and outperform baseline skill learning approaches on new long-horizon tasks in BabyAI, a grid world navigation environment, as well as ALFRED, a household simulation environment.

This paper tackles the emerging challenge of training generative models within a self-consuming loop, wherein successive generations of models are recursively trained on mixtures of real and synthetic data from previous generations. We construct a theoretical framework to rigorously evaluate how this training procedure impacts the data distributions learned by future models, including parametric and non-parametric models. Specifically, we derive bounds on the total variation (TV) distance between the synthetic data distributions produced by future models and the original real data distribution under various mixed training scenarios for diffusion models with a one-hidden-layer neural network score function. Our analysis demonstrates that this distance can be effectively controlled under the condition that mixed training dataset sizes or proportions of real data are large enough. Interestingly, we further unveil a phase transition induced by expanding synthetic data amounts, proving theoretically that while the TV distance exhibits an initial ascent, it declines beyond a threshold point. Finally, we present results for kernel density estimation, delivering nuanced insights such as the impact of mixed data training on error propagation.

Understanding and attributing mental states, known as Theory of Mind (ToM), emerges as a fundamental capability for human social reasoning. While Large Language Models (LLMs) appear to possess certain ToM abilities, the mechanisms underlying these capabilities remain elusive. In this study, we discover that it is possible to linearly decode the belief status from the perspectives of various agents through neural activations of language models, indicating the existence of internal representations of self and others' beliefs. By manipulating these representations, we observe dramatic changes in the models' ToM performance, underscoring their pivotal role in the social reasoning process. Additionally, our findings extend to diverse social reasoning tasks that involve different causal inference patterns, suggesting the potential generalizability of these representations.

The min-max vehicle routing problem (min-max VRP) traverses all given customers by assigning several routes and aims to minimize the length of the longest route. Recently, reinforcement learning (RL)-based sequential planning methods have exhibited advantages in solving efficiency and optimality. However, these methods fail to exploit the problem-specific properties in learning representations, resulting in less effective features for decoding optimal routes. This paper considers the sequential planning process of min-max VRPs as two coupled optimization tasks: customer partition for different routes and customer navigation in each route (i.e., partition and navigation). To effectively process min-max VRP instances, we present a novel attention-based Partition-and-Navigation encoder (P&N Encoder) that learns distinct embeddings for partition and navigation. Furthermore, we utilize an inherent symmetry in decoding routes and develop an effective agent-permutation-symmetric (APS) loss function. Experimental results demonstrate that the proposed Decoupling-Partition-Navigation (DPN) method significantly surpasses existing learning-based methods in both single-depot and multi-depot min-max VRPs. Our code is available at

In privacy-preserving machine learning (PPML), homomorphic encryption (HE) has emerged as a significant primitive, allowing the use of machine learning (ML) models while protecting the confidentiality of input data. Although extensive research has been conducted on implementing PPML with HE by developing the efficient construction of private counterparts to ML models, the efficient HE implementation of embedding layers for token inputs such as words remains inadequately addressed. Thus, our study proposes an efficient algorithm for privacy-preserving embedding via look-up table evaluation with HE(HELUT) by developing an encrypted indicator function (EIF) that assures high precision with the use of the approximate HE scheme(CKKS). Based on the proposed EIF, we propose the CodedHELUT algorithm to facilitate an encrypted embedding layer for the first time. CodedHELUT leverages coded inputs to improve overall efficiency and optimize memory usage. Our comprehensive empirical analysis encompasses both synthetic tables and real-world largescale word embedding models. CodedHELUT algorithm achieves amortized evaluation time of 0.018-0.242s for GloVe6B50d, 0.104-01.298s for GloVe42300d, 0.262-3.283s for GPT-2 and BERT embedding layers while maintaining high precision (16 bits)

Large language models (LLMs) have been routinely used to solve various tasks using step-by-step reasoning. However, the structure of intermediate reasoning steps, or *thoughts*, is rigid and unidirectional, such as chains, trees, or acyclic-directed graphs. Consequently, the resulting inflexible and forward-only reasoning may not address challenging tasks and fail when the LLM frequently gives false responses, i.e., hallucinations. This paper proposes a new reasoning framework, called *Thought Rollback* (TR), allowing LLMs to adaptively build thought structure while maintaining effective reasoning toward problem-solving under hallucinations. The core mechanism of TR is *rolling back thoughts*, which allows LLMs to perform error analysis on thoughts, and thus roll back to any previously mistaken thought for revision. Subsequently, by including such trial-and-error in the prompt to guide the LLM, each rollback leads to one more reliable reasoning path. Therefore, starting with a simple prompt without human annotations, LLM with TR adaptively and gradually explores thoughts for a correct solution. Comprehensive experiments on mathematical problems and multi-task reasoning demonstrate the state-of-the-art performance of TR in terms of problem-solving rate and interaction cost. For instance, the solving rate of GPT-4 with TR outperforms the current best by $9\%$ on the MATH dataset. The source code is available under the folder *examples/ThoughtRollback* of https://github.com/iQua/llmpebase.

Non-IID transfer learning on graphs is crucial in many high-stakes domains. The majority of existing works assume stationary distribution for both source and target domains. However, real-world graphs are intrinsically dynamic, presenting challenges in terms of domain evolution and dynamic discrepancy between source and target domains. To bridge the gap, we shift the problem to the dynamic setting and pose the question: given the *label-rich* source graphs and the *label-scarce* target graphs both observed in previous $T$ timestamps, how can we effectively characterize the evolving domain discrepancy and optimize the generalization performance of the target domain at the incoming $T+1$ timestamp? To answer it, we propose a generalization bound for *dynamic non-IID transfer learning on graphs*, which implies the generalization performance is dominated by domain evolution and domain discrepancy between source and target graphs. Inspired by the theoretical results, we introduce a novel generic framework named EvoluNet. It leverages a transformer-based temporal encoding module to model temporal information of the evolving domains and then uses a dynamic domain unification module to efficiently learn domain-invariant representations across the source and target domains. Finally, EvoluNet outperforms the state-of-the-art models by up to 12.1%, demonstrating its effectiveness in transferring knowledge from dynamic source graphs to dynamic target graphs.

Recent text and image foundation models are incredibly impressive, and these models are attracting an ever-increasing portion of research resources. In this position piece we aim to shift the ML research community's priorities ever so slightly to a different modality: tabular data. Tabular data is the dominant modality in many fields, yet it is given hardly any research attention and significantly lags behind in terms of scale and power. **We believe the time is now to start developing tabular foundation models**, or what we coin a _Large Tabular Model_ (LTM). LTMs could revolutionise the way science and ML use tabular data: not as single datasets that are analyzed in a vacuum, but contextualized with respect to related datasets. The potential impact is far-reaching: from few-shot tabular models to automating data science; from out-of-distribution synthetic data to empowering multidisciplinary scientific discovery. We intend to excite reflections on the modalities we study, and convince some researchers to study Large Tabular Models.

Federated learning (FL) is an emerging machine learning paradigm for preserving data privacy. However, diverse client hardware often has varying computation resources. Such system heterogeneity limits the participation of resource-constrained clients in FL, and hence degrades the global model accuracy. To enable heterogeneous clients to participate in and contribute to FL training, previous works tackle this problem by assigning customized sub-models to individual clients with model pruning, distillation, or low-rank based techniques. Unfortunately, the global model trained by these methods still encounters performance degradation due to heterogeneous sub-model aggregation. Besides, most methods are heuristic-based and lack convergence analysis. In this work, we propose the FedLMT framework to bridge the performance gap, by assigning clients with a homogeneous pre-factorized low-rank model to substantially reduce resource consumption without conducting heterogeneous aggregation. We theoretically prove that the convergence of the low-rank model can guarantee the convergence of the original full model. To further meet clients' personalized resource needs, we extend FedLMT to pFedLMT, by separating model parameters into common and custom ones. Finally, extensive experiments are conducted to verify our theoretical analysis and show that FedLMT and pFedLMT outperform other baselines with much less communication and computation costs.

Class-Incremental Learning (CIL) seeks to learn new concepts without forgetting previously learned knowledge. To achieve this, rehearsal-based methods keep a replay memory consisting of a small number of trained samples from previous tasks. However, recent studies show that rehearsal-based methods are prone to overfitting on rehearsal samples, resulting in poor generalization on previous tasks. Since the generalization error is bounded by the margin on the training dataset, in this paper, we study the generalization by all-layer margin on deep neural networks to alleviate catastrophic forgetting. Specifically, we show that the average margin of the rehearsal samples are smaller during incremental learning. To acquire larger margin thus better generalization on rehearsal samples, we propose Multi-layer Rehearsal Feature Augmentation (MRFA) in rehearsal training to optimize the all-layer margin on rehearsal samples. The proposed method augments the features of rehearsal samples at each layer by gradient ascent step of the current model with respect to the feature. With such augmentations on layer features, the margin on rehearsal samples are larger, rehearsal samples are able to provide more information for refining the decision boundary during incremental learning, thus alleviating catastrophic forgetting. Extensive experiments show the effectiveness of MRFA on various CIL scenarios.

The learning to defer (L2D) framework allows models to defer their decisions to human experts. For L2D, the Bayes optimality is the basic requirement of theoretical guarantees for the design of consistent surrogate loss functions, which requires the minimizer (i.e., learned classifier) by the surrogate loss to be the Bayes optimality. However, we find that the original form of Bayes optimality fails to consider the dependence between the model and the expert, and such a dependence could be further exploited to design a better consistent loss for L2D. In this paper, we provide a new formulation for the Bayes optimality called dependent Bayes optimality, which reveals the dependence pattern in determining whether to defer. Based on the dependent Bayes optimality, we further present a deferral principle for L2D. Following the guidance of the deferral principle, we propose a novel consistent surrogate loss. Comprehensive experimental results on both synthetic and real-world datasets demonstrate the superiority of our proposed method.

Large Language Models (LLMs), renowned for their remarkable performance across diverse domains, present a challenge due to their colossal model size when it comes to practical deployment. In response to this challenge, efforts have been directed toward the application of traditional network pruning techniques to LLMs, uncovering a massive number of parameters can be pruned in one-shot without hurting performance. Building upon insights gained from pre-LLM models, particularly BERT-level language models, prevailing LLM pruning strategies have consistently adhered to the practice of uniformly pruning all layers at equivalent sparsity levels, resulting in robust performance. However, this observation stands in contrast to the prevailing trends observed in the field of vision models, where non-uniform layerwise sparsity typically yields substantially improved results. To elucidate the underlying reasons for this disparity, we conduct a comprehensive analysis of the distribution of token features within LLMs. In doing so, we discover a strong correlation with the emergence of outliers, defined as features exhibiting significantly greater magnitudes compared to their counterparts in feature dimensions. Inspired by this finding, we introduce a novel LLM pruning methodology that incorporates a tailored set of **non-uniform layerwise sparsity ratios** specifically designed for LLM pruning, termed as **O**utlier **W**eighed **L**ayerwise sparsity (**OWL**). The sparsity ratio of OWL is directly proportional to the outlier ratio observed within each layer, facilitating a more effective alignment between layerwise weight sparsity and outlier ratios. Our empirical evaluation, conducted across the LLaMA-V1/V2, Vicuna, OPT, and Mistral, spanning various benchmarks, demonstrates the distinct advantages offered by OWL over previous methods. For instance, OWL exhibits a remarkable performance gain, surpassing the state-of-the-art Wanda and SparseGPT by **61.22** and **6.80** perplexity at a high sparsity level of 70%, respectively, while delivering **2.6$\times$** end-to-end inference speed-up in the DeepSparse inference engine. Code is available at https://github.com/luuyin/OWL.git.

Many neural network architectures are known to be Turing Complete, and can thus, in principle implement arbitrary algorithms. However, Transformers are unique in that they can implement gradient-based learning algorithms *under simple parameter configurations*. This paper provides theoretical and empirical evidence that (non-linear) Transformers naturally learn to implement gradient descent *in function space*, which in turn enable them to learn non-linear functions in context. Our results apply to a broad class of combinations of non-linear architectures and non-linear in-context learning tasks. Additionally, we show that the optimal choice of non-linear activation depends in a natural way on the class of functions that need to be learned.

In recent years, there has been considerable interest in developing machine learning models on graphs to account for topological inductive biases. In particular, recent attention has been given to Gaussian processes on such structures since they can additionally account for uncertainty. However, graphs are limited to modelling relations between two vertices. In this paper, we go beyond this dyadic setting and consider polyadic relations that include interactions between vertices, edges and one of their generalisations, known as cells. Specifically, we propose Gaussian processes on cellular complexes, a generalisation of graphs that captures interactions between these higher-order cells. One of our key contributions is the derivation of two novel kernels, one that generalises the graph Matérn kernel and one that additionally mixes information of different cell types.