ICLR 2024 Papers

Recent advances in self-supervised learning and the Transformer architecture have significantly improved natural language processing (NLP), achieving remarkably low perplexity. However, the growing size of NLP models introduces a memory wall problem during the generation phase. To mitigate this issue, recent efforts have focused on quantizing model weights to sub-4-bit precision while preserving full precision for activations, resulting in practical speed-ups during inference on a single GPU. However, these improvements primarily stem from reduced memory movement, which necessitates a resource-intensive dequantization process rather than actual computational reduction. In this paper, we introduce LUT-GEMM, an efficient kernel for quantized matrix multiplication, which not only eliminates the resource-intensive dequantization process but also reduces computational costs compared to previous kernels for weight-only quantization. Furthermore, we proposed group-wise quantization to offer a flexible trade-off between compression ratio and accuracy. The impact of LUT-GEMM is facilitated by implementing high compression ratios through low-bit quantization and efficient LUT-based operations. We show experimentally that when applied to the OPT-175B model with 3-bit quantization, LUT-GEMM substantially accelerates token generation latency, achieving a remarkable 2.1x improvement on a single GPU when compared to OPTQ, which relies on the costly dequantization process.

Vision Transformers (ViTs) are now flourishing in the computer vision area. Despite the remarkable success, ViTs suffer from high computational costs, which greatly hinder their practical usage. Token reduction, which identifies and discards unimportant tokens during forward propagation, has then been proposed to make ViTs more efficient. For token reduction methodologies, a scoring metric is essential to distinguish between important and unimportant tokens. The attention score from the $\mathrm{[CLS]}$ token, which takes the responsibility to aggregate useful information and form the final output, has been established by prior works as an advantageous choice. Nevertheless, whereas the task pressure is applied at the end of the whole model, token reduction generally starts from very early blocks. Given the long distance in between, in the early blocks, $\mathrm{[CLS]}$ token lacks the impetus to gather task-relevant information, causing somewhat arbitrary attention allocation. This phenomenon, in turn, degrades the reliability of token scoring and substantially compromises the effectiveness of token reduction. Inspired by advances in the domain of dynamic neural networks, in this paper, we introduce Multi-Exit Token Reduction (METR), a simple romance between multi-exit architecture and token reduction—two areas previously considered orthogonal. By injecting early task pressure via multi-exit loss, the $\mathrm{[CLS]}$ token is spurred to collect task-related information in even early blocks, thus bolstering the credibility of $\mathrm{[CLS]}$ attention as a token-scoring metric. Additionally, we employ self-distillation to further refine the quality of early supervision. Extensive experiments substantiate both the existence and effectiveness of the newfound chemistry. Comparative assessments also indicate that METR outperforms state-of-the-art token reduction methods on standard benchmarks, especially under aggressive reduction ratios.

We introduce a novel neural network-based algorithm to compute optimal transport (OT) plans for general cost functionals. In contrast to common Euclidean costs, i.e., $\ell^1$ or $\ell^2$, such functionals provide more flexibility and allow using auxiliary information, such as class labels, to construct the required transport map. Existing methods for general cost functionals are discrete and do not provide an out-of-sample estimation. We address the challenge of designing a continuous OT approach for general cost functionals in high-dimensional spaces, such as images. We construct two example functionals: one to map distributions while preserving the class-wise structure and the other one to preserve the given data pairs. Additionally, we provide the theoretical error analysis for our recovered transport plans. Our implementation is available at \url{https://github.com/machinestein/gnot}

To promote the safe deployment of object detectors, a task of unsupervised out-of-distribution object detection (OOD-OD) is recently proposed, aiming to detect unknown objects during training without reliance on any auxiliary OOD data. To alleviate the impact of lacking OOD data, for this task, one feasible solution is to exploit the known in-distribution (ID) data to synthesize proper OOD information for supervision, which strengthens detectors' discrimination. From the frequency perspective, since the phase generally reflects the content of the input, in this paper, we explore leveraging the phase of ID features to generate expected OOD features involving different content. And a method of Modulated Phase Diffusion (MPD) is proposed, containing a shared forward and two different reverse processes. Specifically, after calculating the phase of the extracted features, to prevent the rapid loss of content in the phase, the forward process gradually performs Gaussian Average on the phase instead of adding noise. The averaged phase and original amplitude are combined to obtain the features taken as the input of the reverse process. Next, one OOD branch is defined to synthesize virtual OOD features by continually enlarging the content discrepancy between the OOD features and original ones. Meanwhile, another modulated branch is designed to generate augmented features owning a similar phase as the original features by scaling and shifting the OOD branch. Both original and augmented features are used for training, enhancing the discrimination. Experimental results on OOD-OD, incremental object detection, and open-set object detection demonstrate the superiorities of our method. The source code will be released at https://github.com/AmingWu/MPD.

We present a diffusion-based image morphing approach with perceptually-uniform sampling (IMPUS) that produces smooth, direct and realistic interpolations given an image pair. The embeddings of two images may lie on distinct conditioned distributions of a latent diffusion model, especially when they have significant semantic difference. To bridge this gap, we interpolate in the locally linear and continuous text embedding space and Gaussian latent space. We first optimize the endpoint text embeddings and then map the images to the latent space using a probability flow ODE. Unlike existing work that takes an indirect morphing path, we show that the model adaptation yields a direct path and suppresses ghosting artifacts in the interpolated images. To achieve this, we propose a heuristic bottleneck constraint based on a novel relative perceptual path diversity score that automatically controls the bottleneck size and balances the diversity along the path with its directness. We also propose a perceptually-uniform sampling technique that enables visually smooth changes between the interpolated images. Extensive experiments validate that our IMPUS can achieve smooth, direct, and realistic image morphing and is adaptable to several other generative tasks.

Sampling-based algorithms, which eliminate "unimportant" computations during forward and/or backpropagation (BP), offer potential solutions to accelerate neural network training. However, since sampling introduces approximations to training, such algorithms may not consistently maintain accuracy across various tasks. In this work, we introduce a variance-controlled adaptive sampling (VCAS) method designed to minimize the computational load of BP. VCAS computes an unbiased stochastic gradient with fine-grained layerwise importance sampling in data dimension for activation gradient calculation and leverage score sampling in token dimension for weight gradient calculation. To preserve accuracy, we control the additional variance introduced by learning the sample ratio jointly with model parameters during training. We assessed VCAS on multiple fine-tuning and pre-training tasks in both vision and natural language domains. On all the tasks, VCAS can preserve the original training loss trajectory and validation accuracy with an up to 73.87% FLOPs reduction of BP and 49.58% FLOPs reduction of the whole training process. The implementation is available at https://github.com/thu-ml/VCAS.

Large language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc. While their performance is impressive, the computational footprint due to their vast number of parameters can be prohibitive. Existing solutions such as SparseGPT and Wanda attempt to alleviate this issue through weight pruning. However, their layer-wise approach results in significant perturbation to the model's output and requires meticulous hyperparameter tuning, such as the pruning rate, which can adversely affect overall model performance. To address this, this paper introduces a novel LLM pruning technique dubbed blockwise parameter-efficient sparsity allocation (BESA) by applying a blockwise reconstruction loss. In contrast to the typical layer-wise pruning techniques, BESA is characterized by two distinctive attributes: i) it targets the overall pruning error with respect to individual transformer blocks, and ii) it allocates layer-specific sparsity in a differentiable manner, both of which ensure reduced performance degradation after pruning. Our experiments show that BESA achieves state-of-the-art performance, efficiently pruning LLMs like LLaMA1, and LLaMA2 with 7B to 70B parameters on a single A100 GPU in just five hours. Code is available at [here](https://github.com/LinkAnonymous/BESA).

Second-order optimization has been developed to accelerate the training of deep neural networks and it is being applied to increasingly larger-scale models. In this study, towards training on further larger scales, we identify a specific parameterization for second-order optimization that promotes feature learning in a stable manner even if the network width increases significantly. Inspired by a maximal update parametrization, we consider a one-step update of the gradient and reveal the appropriate scales of hyperparameters including random initialization, learning rates, and damping terms. Our approach covers two major second-order optimization algorithms, K-FAC and Shampoo, and we demonstrate that our parametrization achieves higher generalization performance in feature learning. In particular, it enables us to transfer the hyperparameters across models with different widths.

A promising approach for improving the performance of vision-language models like CLIP for image classification is to extend the class descriptions (i.e., prompts) with related attributes, e.g., using brown sparrow instead of sparrow. However, current zero-shot methods select a subset of attributes regardless of commonalities between the target classes, potentially providing no useful information that would have helped to distinguish between them. For instance, they may use color instead of bill shape to distinguish between sparrows and wrens, which are both brown. We propose Follow-up Differential Descriptions (FuDD), a zero-shot approach that tailors the class descriptions to each dataset and leads to additional attributes that better differentiate the target classes. FuDD first identifies the ambiguous classes for each image, and then uses a Large Language Model (LLM) to generate new class descriptions that differentiate between them. The new class descriptions resolve the initial ambiguity and help predict the correct label. In our experiments, FuDD consistently outperforms generic description ensembles and naive LLM-generated descriptions on 12 datasets. We show that differential descriptions are an effective tool to resolve class ambiguities, which otherwise significantly degrade the performance. We also show that high quality natural language class descriptions produced by FuDD result in comparable performance to few-shot adaptation methods.

We focus on the self-supervised discovery of manipulation concepts that can be adapted and reassembled to address various robotic tasks. We propose that the decision to conceptualize a physical procedure should not depend on how we name it (semantics) but rather on the significance of the informativeness in its representation regarding the low-level physical state and state changes. We model manipulation concepts -- discrete symbols -- as generative and discriminative goals and derive metrics that can autonomously link them to meaningful sub-trajectories from noisy, unlabeled demonstrations. Specifically, we employ a trainable codebook containing encodings --symbols -- capable of synthesizing the end-state of a sub-trajectory given the current state (generative informativeness). Moreover, the encoding corresponding to a particular sub-trajectory should differentiate the state within and outside it and confidently predict the subsequent action based on the gradient of its discriminative score (discriminative informativeness). These metrics, which do not rely on human annotation, can be seamlessly integrated into a VQ-VAE framework, enabling the partitioning of demonstrations into semantically consistent sub-trajectories, fulfilling the purpose of discovering manipulation concepts and the corresponding (sub)-goal states. We evaluate the effectiveness of the learned concepts by training policies that utilize them as guidance, demonstrating superior performance compared to other baselines. Additionally, our discovered manipulation concepts compare favorably to human-annotated ones, while saving much manual effort. The code and trained models will be made public.

Spiking Neural Networks (SNNs) have garnered considerable attention due to their energy efficiency and unique biological characteristics. However, the widely adopted Leaky Integrate-and-Fire (LIF) model, as the mainstream neuron model in current SNN research, has been revealed to exhibit significant deficiencies in deep-layer gradient calculation and capturing global information on the time dimension. In this paper, we propose the Learnable Multi-hierarchical (LM-H) model to address these issues by dynamically regulating its membrane-related factors. We point out that the LM-H model fully encompasses the information representation range of the LIF model while offering the flexibility to adjust the extraction ratio between historical and current information. Additionally, we theoretically demonstrate the effectiveness of the LM-H model and the functionality of its internal parameters, and propose a progressive training algorithm tailored specifically for the LM-H model. Furthermore, we devise an efficient training framework for our novel advanced model, encompassing hybrid training and time-slicing online training. Through extensive experiments on various datasets, we validate the remarkable superiority of our model and training algorithm compared to previous state-of-the-art approaches. Code is available at [https://github.com/hzc1208/STBP_LMH](https://github.com/hzc1208/STBP_LMH).

We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learning into a bandit problem, achieving both theoretical and empirical success. However, the performance and computational costs of these methods may be susceptible to the number of classes, denoted as $K$, due to this transformation. Therefore, this paper seeks to answer the question: "How can we mitigate the adverse impacts of $K$ while retaining the advantages of principled exploration and provable performance guarantees in active learning?" To tackle this challenge, we propose two algorithms based on the newly designed exploitation and exploration neural networks for stream-based and pool-based active learning. Subsequently, we provide theoretical performance guarantees for both algorithms in a non-parametric setting, demonstrating a slower error-growth rate concerning $K$ for the proposed approaches. We use extensive experiments to evaluate the proposed algorithms, which consistently outperform state-of-the-art baselines.

Federated learning (FL) is a distributed machine learning framework where the global model of a central server is trained via multiple collaborative steps by participating clients without sharing their data. While being a flexible framework, where the distribution of local data, participation rate, and computing power of each client can greatly vary, such flexibility gives rise to many new challenges, especially in the hyperparameter tuning on the client side. We propose $\Delta$-SGD, a simple step size rule for SGD that enables each client to use its own step size by adapting to the local smoothness of the function each client is optimizing. We provide theoretical and empirical results where the benefit of the client adaptivity is shown in various FL scenarios.

Signal restoration is an important constrained optimization problem with significant applications in various domains. Although non-convex constrained optimization problems have been shown to perform better than convex counterparts in terms of reconstruction quality, convex constrained optimization problems have been preferably for its global optima guarantees. Despite the success of non-convex methods in a large number of applications, it is not an overstatement to say that there is little or no hope for non-convex problems to ensure global optima. In this paper, for the first time, we develop invex constrained optimization theory to mitigate the loss of guarantees for global optima in non-convex constrained inverse problems, where the invex function is a mapping where any critical point is a global minimizer. We also develop relevant theories to extend the global optima guarantee to a set of quasi-invex functions - the largest optimizable mappings. More specifically, we propose a family of invex/quasi-invex of functions for handling constrained inverse problems using the non-convex setting along with guarantees for their global optima. Our experimental evaluation shows that the proposed approach is very promising and can aid in extending existing convex optimization algorithms, such as the alternating direction method of multipliers, and accelerated proximal gradient methods.

Predicting physical properties of materials from their crystal structures is a fundamental problem in materials science. In peripheral areas such as the prediction of molecular properties, fully connected attention networks have been shown to be successful. However, unlike these finite atom arrangements, crystal structures are infinitely repeating, periodic arrangements of atoms, whose fully connected attention results in *infinitely connected attention*. In this work, we show that this infinitely connected attention can lead to a computationally tractable formulation, interpreted as *neural potential summation*, that performs infinite interatomic potential summations in a deeply learned feature space. We then propose a simple yet effective Transformer-based encoder architecture for crystal structures called *Crystalformer*. Compared to an existing Transformer-based model, the proposed model requires only 29.4% of the number of parameters, with minimal modifications to the original Transformer architecture. Despite the architectural simplicity, the proposed method outperforms state-of-the-art methods for various property regression tasks on the Materials Project and JARVIS-DFT datasets.

Image-Text Matching (ITM) task, a fundamental vision-language (VL) task, suffers from the inherent ambiguity arising from multiplicity and imperfect annotations. Deterministic functions are not sufficiently powerful to capture ambiguity, prompting the exploration of probabilistic embeddings to tackle the challenge. However, the existing probabilistic ITM approach encounters two key shortcomings; the burden of heavy computations due to the Monte Carlo approximation, and the loss saturation issue in the face of abundant false negatives. To overcome the issues, this paper presents an improved Probabilistic Cross-Modal Embeddings (named PCME++) by introducing a new probabilistic distance with a closed-form solution. In addition, two optimization techniques are proposed to enhance PCME++ further: first, the incorporation of pseudo-positives to prevent the negative effect under massive false negatives; second, mixed sample data augmentation for probabilistic matching. Experimental results on MS-COCO Caption and two extended benchmarks, CxC and ECCV Caption, demonstrate the effectiveness of PCME++ compared to state-of-the-art ITM methods. The robustness of PCME++ is also evaluated under noisy image-text correspondences. In addition, the potential applicability of PCME++ in automatic prompt-filtering for zero-shot classification is shown. The code is available at https://github.com/naver-ai/pcmepp.

Unsupervised domain adaptation (UDA) involves adapting a model trained on a label-rich source domain to an unlabeled target domain. However, in real-world scenarios, the absence of target-domain labels makes it challenging to evaluate the performance of UDA models. Furthermore, prevailing UDA methods relying on adversarial training and self-training could lead to model degeneration and negative transfer, further exacerbating the evaluation problem. In this paper, we propose a novel metric called the Transfer Score to address these issues. The proposed metric enables the unsupervised evaluation of UDA models by assessing the spatial uniformity of the classifier via model parameters, as well as the transferability and discriminability of deep representations. Based on the metric, we achieve three novel objectives without target-domain labels: (1) selecting the best UDA method from a range of available options, (2) optimizing hyperparameters of UDA models to prevent model degeneration, and (3) identifying which checkpoint of UDA model performs optimally. Our work bridges the gap between data-level UDA research and practical UDA scenarios, enabling a realistic assessment of UDA model performance. We validate the effectiveness of our metric through extensive empirical studies on UDA datasets of different scales and imbalanced distributions. The results demonstrate that our metric robustly achieves the aforementioned goals.

Despite the promising few-shot ability of large language models (LLMs), the standard paradigm of In-context Learning (ICL) suffers the disadvantages of susceptibility to selected demonstrations and the intricacy to generate these demonstrations. In this paper, we raise the fundamental question that whether human-generated demonstrations are necessary for ICL. To answer this question, we propose self-contemplation prompting strategy (SEC), a paradigm free from human-crafted demonstrations. The key point of SEC is that, instead of using hand-crafted examples as demonstrations in ICL, SEC asks LLMs to first create demonstrations on their own, based on which the final output is generated. SEC is a flexible framework and can be adapted to both the vanilla ICL and the chain-of-thought (CoT), but with greater ease: as the manual-generation process of both examples and rationale can be saved. Extensive experiments in arithmetic reasoning, commonsense reasoning, multi-task language understanding, and code generation benchmarks, show that SEC, which does not require hand-crafted demonstrations, significantly outperforms the zero-shot learning strategy, and achieves comparable results to ICL with hand-crafted demonstrations. This demonstrates that, for many tasks, contemporary LLMs possess a sufficient level of competence to exclusively depend on their own capacity for decision making, removing the need for external training data.

We study infinite-horizon average-reward Markov decision processes (AMDPs) in the context of general function approximation. Specifically, we propose a novel algorithmic framework named Local-fitted Optimization with OPtimism (LOOP), which incorporates both model-based and value-based incarnations. In particular, LOOP features a novel construction of confidence sets and a low-switching policy updating scheme, which are tailored to the average-reward and function approximation setting. Moreover, for AMDPs, we propose a novel complexity measure --- average-reward generalized eluder coefficient (AGEC) --- which captures the challenge of exploration in AMDPs with general function approximation. Such a complexity measure encompasses almost all previously known tractable AMDP models, such as linear AMDPs and linear mixture AMDPs, and also includes newly identified cases such as kernel AMDPs and AMDPs with Bellman eluder dimensions. Using AGEC, we prove that LOOP achieves a sublinear $\tilde{\mathcal{O}}(\mathrm{poly}(d, \mathrm{sp}(V^*)) \sqrt{T\beta} )$ regret, where $d$ and $\beta$ correspond to AGEC and log-covering number of the hypothesis class respectively, $\mathrm{sp}(V^*)$ is the span of the optimal state bias function, $T$ denotes the number of steps, and $\tilde{\mathcal{O}} (\cdot) $ omits logarithmic factors. When specialized to concrete AMDP models, our regret bounds are comparable to those established by the existing algorithms designed specifically for these special cases. To the best of our knowledge, this paper presents the first comprehensive theoretical framework capable of handling nearly all AMDPs.