Search

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While alternate classes of models have been explored, we have limited mathematical understanding of their fundamental power and limitations. In this paper we focus on Generative Masked Language Models (GMLMs), a non-autoregressive paradigm in which we train a model to fit conditional probabilities of the data distribution via masking, which are subsequently used as inputs to a Markov Chain to draw samples from the model, These models empirically strike a promising speed-quality trade-off as each step can be typically parallelized by decoding the entire sequence in parallel. We develop a mathematical framework for analyzing and improving such models which sheds light on questions of sample complexity and inference speed and quality. Empirically, we adapt the T5 model for iteratively-refined parallel decoding, achieving 2-3x speedup in machine translation with minimal sacrifice in quality compared with autoregressive models. We run careful ablation experiments to give recommendations on key design choices, and make fine-grained observations on the common error modes in connection with our theory. Our mathematical analyses and empirical observations characterize both potentials and limitations of this approach, and can be applied to future works on improving understanding and performance of GMLMs. Our codes are released at https://github.com/google-research/google-research/tree/master/padir, Comment: ICML 2024

Cross-Encoder (CE) and Dual-Encoder (DE) models are two fundamental approaches for query-document relevance in information retrieval. To predict relevance, CE models use joint query-document embeddings, while DE models maintain factorized query and document embeddings; usually, the former has higher quality while the latter benefits from lower latency. Recently, late-interaction models have been proposed to realize more favorable latency-quality tradeoffs, by using a DE structure followed by a lightweight scorer based on query and document token embeddings. However, these lightweight scorers are often hand-crafted, and there is no understanding of their approximation power; further, such scorers require access to individual document token embeddings, which imposes an increased latency and storage burden. In this paper, we propose novel learnable late-interaction models (LITE) that resolve these issues. Theoretically, we prove that LITE is a universal approximator of continuous scoring functions, even for relatively small embedding dimension. Empirically, LITE outperforms previous late-interaction models such as ColBERT on both in-domain and zero-shot re-ranking tasks. For instance, experiments on MS MARCO passage re-ranking show that LITE not only yields a model with better generalization, but also lowers latency and requires 0.25x storage compared to ColBERT.

Recently, there has been increasing interest in efficient pretraining paradigms for training Transformer-based models. Several recent approaches use smaller models to initialize larger models in order to save computation (e.g., stacking and fusion). In this work, we study the fundamental question of how to select the best growing strategy from a given pool of growing strategies. Prior works have extensively focused on loss- and/or function-preserving behavior at initialization or simply performance at the end of training. Instead, we identify that behavior at initialization can be misleading as a predictor of final performance and present an alternative perspective based on early training dynamics, which we call "landscape-aware growing (LAG)". We perform extensive analysis of correlation of the final performance with performance in the initial steps of training and find early and more accurate predictions of the optimal growing strategy (i.e., with only a small "lag" after initialization). This perspective also motivates an adaptive strategy for gradual stacking.

Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a deferral rule that invokes the larger model only for "hard" inputs, while speculative decoding uses speculative execution to primarily invoke the larger model in parallel verification mode. These mechanisms offer different benefits: empirically, cascades are often capable of yielding better quality than even the larger model, while theoretically, speculative decoding offers a guarantee of quality-neutrality. In this paper, we leverage the best of both these approaches by designing new speculative cascading techniques that implement their deferral rule through speculative execution. We characterize the optimal deferral rule for our speculative cascades, and employ a plug-in approximation to the optimal rule. Through experiments with T5 models on benchmark language tasks, we show that the proposed approach yields better cost-quality trade-offs than cascading and speculative decoding baselines.

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality tradeoffs: here, a small model is invoked for most "easy" instances, while a few "hard" instances are deferred to the large model. While the principles underpinning cascading are well-studied for classification tasks - with deferral based on predicted class uncertainty favored theoretically and practically - a similar understanding is lacking for generative LM tasks. In this work, we initiate a systematic study of deferral rules for LM cascades. We begin by examining the natural extension of predicted class uncertainty to generative LM tasks, namely, the predicted sequence uncertainty. We show that this measure suffers from the length bias problem, either over- or under-emphasizing outputs based on their lengths. This is because LMs produce a sequence of uncertainty values, one for each output token; and moreover, the number of output tokens is variable across examples. To mitigate this issue, we propose to exploit the richer token-level uncertainty information implicit in generative LMs. We argue that naive predicted sequence uncertainty corresponds to a simple aggregation of these uncertainties. By contrast, we show that incorporating token-level uncertainty through learned post-hoc deferral rules can significantly outperform such simple aggregation strategies, via experiments on a range of natural language benchmarks with FLAN-T5 models. We further show that incorporating embeddings from the smaller model and intermediate layers of the larger model can give an additional boost in the overall cost-quality tradeoff.

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as a method to improve inference speed of language models by simultaneously predicting multiple future tokens, termed block drafts, which are subsequently verified and conditionally accepted by the autoregressive model. This paper contributes to the understanding and improvement of block drafts in two ways. First, we analyze the token distributions produced by multiple prediction heads. Secondly, we leverage this analysis to develop algorithms to improve BPD inference speed by refining the block drafts using n-gram and neural language models. Experiments demonstrate that refined block drafts yield a +5-21% increase in block efficiency (i.e., the number of accepted tokens from the block draft) across diverse datasets.

This paper introduces SOAR: Spilling with Orthogonality-Amplified Residuals, a novel data indexing technique for approximate nearest neighbor (ANN) search. SOAR extends upon previous approaches to ANN search, such as spill trees, that utilize multiple redundant representations while partitioning the data to reduce the probability of missing a nearest neighbor during search. Rather than training and computing these redundant representations independently, however, SOAR uses an orthogonality-amplified residual loss, which optimizes each representation to compensate for cases where other representations perform poorly. This drastically improves the overall index quality, resulting in state-of-the-art ANN benchmark performance while maintaining fast indexing times and low memory consumption.

Large language models (LLMs) have demonstrated strong results on a range of NLP tasks. Typically, outputs are obtained via autoregressive sampling from the LLM's underlying distribution. Building on prior work on Minimum Bayes Risk Decoding, we show that this inference strategy can be suboptimal for a range of regression and scoring tasks, and associated evaluation metrics. As a remedy, we propose metric aware LLM inference: a decision theoretic approach optimizing for custom regression and scoring metrics at inference time. We report improvements over baselines on academic benchmarks and publicly available models., Comment: 15 pages

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other hand, recent works show that LLMs can maintain quality with significant sparsity/redundancy in the feedforward (FFN) layers by appropriately training the model to operate on a top-$k$ fraction of rows/columns (where $k \approx 0.05$), there by suggesting a way to reduce the transfer of model parameters, and hence latency. However, exploiting this sparsity for improving latency is hindered by the fact that identifying top rows/columns is data-dependent and is usually performed using full matrix operations, severely limiting potential gains. To address these issues, we introduce HiRE (High Recall Approximate Top-k Estimation). HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47\times$ on a single TPUv5e device.

The autoregressive nature of conventional large language models (LLMs) inherently limits inference speed, as tokens are generated sequentially. While speculative and parallel decoding techniques attempt to mitigate this, they face limitations: either relying on less accurate smaller models for generation or failing to fully leverage the base LLM's representations. We introduce a novel architecture, Tandem transformers, to address these issues. This architecture uniquely combines (1) a small autoregressive model and (2) a large model operating in block mode (processing multiple tokens simultaneously). The small model's predictive accuracy is substantially enhanced by granting it attention to the large model's richer representations. On the PaLM2 pretraining dataset, a tandem of PaLM2-Bison and PaLM2-Gecko demonstrates a 3.3% improvement in next-token prediction accuracy over a standalone PaLM2-Gecko, offering a 1.16x speedup compared to a PaLM2-Otter model with comparable downstream performance. We further incorporate the tandem model within the speculative decoding (SPEED) framework where the large model validates tokens from the small model. This ensures that the Tandem of PaLM2-Bison and PaLM2-Gecko achieves substantial speedup (around 1.14x faster than using vanilla PaLM2-Gecko in SPEED) while maintaining identical downstream task accuracy.

Recent developments in large language models have sparked interest in efficient pretraining methods. A recent effective paradigm is to perform stage-wise training, where the size of the model is gradually increased over the course of training (e.g. gradual stacking (Reddi et al., 2023)). While the resource and wall-time savings are appealing, it has limitations, particularly the inability to evaluate the full model during earlier stages, and degradation in model quality due to smaller model capacity in the initial stages. In this work, we propose an alternative framework, progressive subnetwork training, that maintains the full model throughout training, but only trains subnetworks within the model in each step. We focus on a simple instantiation of this framework, Random Path Training (RaPTr) that only trains a sub-path of layers in each step, progressively increasing the path lengths in stages. RaPTr achieves better pre-training loss for BERT and UL2 language models while requiring 20-33% fewer FLOPs compared to standard training, and is competitive or better than other efficient training methods. Furthermore, RaPTr shows better downstream performance on UL2, improving QA tasks and SuperGLUE by 1-5% compared to standard training and stacking. Finally, we provide a theoretical basis for RaPTr to justify (a) the increasing complexity of subnetworks in stages, and (b) the stability in loss across stage transitions due to residual connections and layer norm.

Pre-training large language models is known to be extremely resource intensive and often times inefficient, under-utilizing the information encapsulated in the training text sequences. In this paper, we present SpacTor, a new training procedure consisting of (1) a hybrid objective combining span corruption (SC) and token replacement detection (RTD), and (2) a two-stage curriculum that optimizes the hybrid objective over the initial $\tau$ iterations, then transitions to standard SC loss. We show empirically that the effectiveness of the hybrid objective is tied to the two-stage pre-training schedule, and provide extensive analysis on why this is the case. In our experiments with encoder-decoder architectures (T5) on a variety of NLP tasks, SpacTor-T5 yields the same downstream performance as standard SC pre-training, while enabling a 50% reduction in pre-training iterations and 40% reduction in total FLOPs. Alternatively, given the same amount of computing budget, we find that SpacTor results in significantly improved downstream benchmark performance., Comment: 9+13 pages, 5 figures

The success of deep learning hinges on enormous data and large models, which require labor-intensive annotations and heavy computation costs. Subset selection is a fundamental problem that can play a key role in identifying smaller portions of the training data, which can then be used to produce similar models as the ones trained with full data. Two prior methods are shown to achieve impressive results: (1) margin sampling that focuses on selecting points with high uncertainty, and (2) core-sets or clustering methods such as k-center for informative and diverse subsets. We are not aware of any work that combines these methods in a principled manner. To this end, we develop a novel and efficient factor 3-approximation algorithm to compute subsets based on the weighted sum of both k-center and uncertainty sampling objective functions. To handle large datasets, we show a parallel algorithm to run on multiple machines with approximation guarantees. The proposed algorithm achieves similar or better performance compared to other strong baselines on vision datasets such as CIFAR-10, CIFAR-100, and ImageNet., Comment: data selection, k-center, subset selection

Answering complex natural language questions often necessitates multi-step reasoning and integrating external information. Several systems have combined knowledge retrieval with a large language model (LLM) to answer such questions. These systems, however, suffer from various failure cases, and we cannot directly train them end-to-end to fix such failures, as interaction with external knowledge is non-differentiable. To address these deficiencies, we define a ReAct-style LLM agent with the ability to reason and act upon external knowledge. We further refine the agent through a ReST-like method that iteratively trains on previous trajectories, employing growing-batch reinforcement learning with AI feedback for continuous self-improvement and self-distillation. Starting from a prompted large model and after just two iterations of the algorithm, we can produce a fine-tuned small model that achieves comparable performance on challenging compositional question-answering benchmarks with two orders of magnitude fewer parameters., Comment: 19 pages, 4 figures, 4 tables, 8 listings

As with many machine learning problems, the progress of image generation methods hinges on good evaluation metrics. One of the most popular is the Frechet Inception Distance (FID). FID estimates the distance between a distribution of Inception-v3 features of real images, and those of images generated by the algorithm. We highlight important drawbacks of FID: Inception's poor representation of the rich and varied content generated by modern text-to-image models, incorrect normality assumptions, and poor sample complexity. We call for a reevaluation of FID's use as the primary quality metric for generated images. We empirically demonstrate that FID contradicts human raters, it does not reflect gradual improvement of iterative text-to-image models, it does not capture distortion levels, and that it produces inconsistent results when varying the sample size. We also propose an alternative new metric, CMMD, based on richer CLIP embeddings and the maximum mean discrepancy distance with the Gaussian RBF kernel. It is an unbiased estimator that does not make any assumptions on the probability distribution of the embeddings and is sample efficient. Through extensive experiments and analysis, we demonstrate that FID-based evaluations of text-to-image models may be unreliable, and that CMMD offers a more robust and reliable assessment of image quality., Comment: Code is available at: https://github.com/google-research/google-research/tree/master/cmmd

Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based classification models, bias and variance are \emph{aligned} at a sample level, where squared bias is approximately \emph{equal} to variance for correctly classified sample points. We present empirical evidence confirming this phenomenon in a variety of deep learning models and datasets. Moreover, we study this phenomenon from two theoretical perspectives: calibration and neural collapse. We first show theoretically that under the assumption that the models are well calibrated, we can observe the bias-variance alignment. Second, starting from the picture provided by the neural collapse theory, we show an approximate correlation between bias and variance.

Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according to the target model distribution. However, identifying a compact draft model that is well-aligned with the target model is challenging. To tackle this issue, we propose DistillSpec that uses knowledge distillation to better align the draft model with the target model, before applying SD. DistillSpec makes two key design choices, which we demonstrate via systematic study to be crucial to improving the draft and target alignment: utilizing on-policy data generation from the draft model, and tailoring the divergence function to the task and decoding strategy. Notably, DistillSpec yields impressive 10 - 45% speedups over standard SD on a range of standard benchmarks, using both greedy and non-greedy sampling. Furthermore, we combine DistillSpec with lossy SD to achieve fine-grained control over the latency vs. task performance trade-off. Finally, in practical scenarios with models of varying sizes, first using distillation to boost the performance of the target model and then applying DistillSpec to train a well-aligned draft model can reduce decoding latency by 6-10x with minimal performance drop, compared to standard decoding without distillation.

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels. To carefully study this issue, Feldman proposed a metric to quantify the degree of memorisation of individual training examples, and empirically computed the corresponding memorisation profile of a ResNet on image classification bench-marks. While an exciting first glimpse into what real-world models memorise, this leaves open a fundamental question: do larger neural models memorise more? We present a comprehensive empirical analysis of this question on image classification benchmarks. We find that training examples exhibit an unexpectedly diverse set of memorisation trajectories across model sizes: most samples experience decreased memorisation under larger models, while the rest exhibit cap-shaped or increasing memorisation. We show that various proxies for the Feldman memorization score fail to capture these fundamental trends. Lastly, we find that knowledge distillation, an effective and popular model compression technique, tends to inhibit memorisation, while also improving generalisation. Specifically, memorisation is mostly inhibited on examples with increasing memorisation trajectories, thus pointing at how distillation improves generalisation.

Preventing the performance decay of Transformers on inputs longer than those used for training has been an important challenge in extending the context length of these models. Though the Transformer architecture has fundamentally no limits on the input sequence lengths it can process, the choice of position encoding used during training can limit the performance of these models on longer inputs. We propose a novel functional relative position encoding with progressive interpolation, FIRE, to improve Transformer generalization to longer contexts. We theoretically prove that this can represent some of the popular relative position encodings, such as T5's RPE, Alibi, and Kerple. We next empirically show that FIRE models have better generalization to longer contexts on both zero-shot language modeling and long text benchmarks., Comment: 26 pages; ICLR 2024 camera ready version

Language models generate responses by producing a series of tokens in immediate succession: the $(K+1)^{th}$ token is an outcome of manipulating $K$ hidden vectors per layer, one vector per preceding token. What if instead we were to let the model manipulate say, $K+10$ hidden vectors, before it outputs the $(K+1)^{th}$ token? We operationalize this idea by performing training and inference on language models with a (learnable) $\textit{pause}$ token, a sequence of which is appended to the input prefix. We then delay extracting the model's outputs until the last pause token is seen, thereby allowing the model to process extra computation before committing to an answer. We empirically evaluate $\textit{pause-training}$ on decoder-only models of 1B and 130M parameters with causal pretraining on C4, and on downstream tasks covering reasoning, question-answering, general understanding and fact recall. Our main finding is that inference-time delays show gains when the model is both pre-trained and finetuned with delays. For the 1B model, we witness gains on 8 of 9 tasks, most prominently, a gain of $18\%$ EM score on the QA task of SQuAD, $8\%$ on CommonSenseQA and $1\%$ accuracy on the reasoning task of GSM8k. Our work raises a range of conceptual and practical future research questions on making delayed next-token prediction a widely applicable new paradigm., Comment: Published at ICLR 2024

Modern text-to-image generation models produce high-quality images that are both photorealistic and faithful to the text prompts. However, this quality comes at significant computational cost: nearly all of these models are iterative and require running sampling multiple times with large models. This iterative process is needed to ensure that different regions of the image are not only aligned with the text prompt, but also compatible with each other. In this work, we propose a light-weight approach to achieving this compatibility between different regions of an image, using a Markov Random Field (MRF) model. We demonstrate the effectiveness of this method on top of the latent token-based Muse text-to-image model. The MRF richly encodes the compatibility among image tokens at different spatial locations to improve quality and significantly reduce the required number of Muse sampling steps. Inference with the MRF is significantly cheaper, and its parameters can be quickly learned through back-propagation by modeling MRF inference as a differentiable neural-network layer. Our full model, MarkovGen, uses this proposed MRF model to both speed up Muse by 1.5X and produce higher quality images by decreasing undesirable image artifacts.

Cascades are a classical strategy to enable inference cost to vary adaptively across samples, wherein a sequence of classifiers are invoked in turn. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. One simple deferral rule employs the confidence of the current classifier, e.g., based on the maximum predicted softmax probability. Despite being oblivious to the structure of the cascade -- e.g., not modelling the errors of downstream models -- such confidence-based deferral often works remarkably well in practice. In this paper, we seek to better understand the conditions under which confidence-based deferral may fail, and when alternate deferral strategies can perform better. We first present a theoretical characterisation of the optimal deferral rule, which precisely characterises settings under which confidence-based deferral may suffer. We then study post-hoc deferral mechanisms, and demonstrate they can significantly improve upon confidence-based deferral in settings where (i) downstream models are specialists that only work well on a subset of inputs, (ii) samples are subject to label noise, and (iii) there is distribution shift between the train and test set., Comment: NeurIPS 2023

In this short note we consider random fully connected ReLU networks of width $n$ and depth $L$ equipped with a mean-field weight initialization. Our purpose is to study the dependence on $n$ and $L$ of the maximal update ($\mu$P) learning rate, the largest learning rate for which the mean squared change in pre-activations after one step of gradient descent remains uniformly bounded at large $n,L$. As in prior work on $\mu$P of Yang et. al., we find that this maximal update learning rate is independent of $n$ for all but the first and last layer weights. However, we find that it has a non-trivial dependence of $L$, scaling like $L^{-3/2}.$

The impressive generalization performance of modern neural networks is attributed in part to their ability to implicitly memorize complex training patterns. Inspired by this, we explore a novel mechanism to improve model generalization via explicit memorization. Specifically, we propose the residual-memorization (ResMem) algorithm, a new method that augments an existing prediction model (e.g. a neural network) by fitting the model's residuals with a $k$-nearest neighbor based regressor. The final prediction is then the sum of the original model and the fitted residual regressor. By construction, ResMem can explicitly memorize the training labels. Empirically, we show that ResMem consistently improves the test set generalization of the original prediction model across various standard vision and natural language processing benchmarks. Theoretically, we formulate a stylized linear regression problem and rigorously show that ResMem results in a more favorable test risk over the base predictor.

Knowledge distillation (KD) has been widely used to improve the test accuracy of a "student" network, by training it to mimic the soft probabilities of a trained "teacher" network. Yet, it has been shown in recent work that, despite being trained to fit the teacher's probabilities, the student may not only significantly deviate from the teacher probabilities, but may also outdo than the teacher in performance. Our work aims to reconcile this seemingly paradoxical observation. Specifically, we characterize the precise nature of the student-teacher deviations, and argue how they can co-occur with better generalization. First, through experiments on image and language data, we identify that these probability deviations correspond to the student systematically exaggerating the confidence levels of the teacher. Next, we theoretically and empirically establish another form of exaggeration in some simple settings: KD exaggerates the implicit bias of gradient descent in converging faster along the top eigendirections of the data. Finally, we tie these two observations together: we demonstrate that the exaggerated bias of KD can simultaneously result in both (a) the exaggeration of confidence and (b) the improved generalization of the student, thus offering a resolution to the apparent paradox. Our analysis brings existing theory and practice closer by considering the role of gradient descent in KD and by demonstrating the exaggerated bias effect in both theoretical and empirical settings.

Real-world classifiers can benefit from the option of abstaining from predicting on samples where they have low confidence. Such abstention is particularly useful on samples which are close to the learned decision boundary, or which are outliers with respect to the training sample. These settings have been the subject of extensive but disjoint study in the selective classification (SC) and out-of-distribution (OOD) detection literature. Recent work on selective classification with OOD detection (SCOD) has argued for the unified study of these problems; however, the formal underpinnings of this problem are still nascent, and existing techniques are heuristic in nature. In this paper, we propose new plugin estimators for SCOD that are theoretically grounded, effective, and generalise existing approaches from the SC and OOD detection literature. In the course of our analysis, we formally explicate how na\"{i}ve use of existing SC and OOD detection baselines may be inadequate for SCOD. We empirically demonstrate that our approaches yields competitive SC and OOD detection performance compared to baselines from both literatures.

Despite the popularity and efficacy of knowledge distillation, there is limited understanding of why it helps. In order to study the generalization behavior of a distilled student, we propose a new theoretical framework that leverages supervision complexity: a measure of alignment between teacher-provided supervision and the student's neural tangent kernel. The framework highlights a delicate interplay among the teacher's accuracy, the student's margin with respect to the teacher predictions, and the complexity of the teacher predictions. Specifically, it provides a rigorous justification for the utility of various techniques that are prevalent in the context of distillation, such as early stopping and temperature scaling. Our analysis further suggests the use of online distillation, where a student receives increasingly more complex supervision from teachers in different stages of their training. We demonstrate efficacy of online distillation and validate the theoretical findings on a range of image classification benchmarks and model architectures., Comment: Published at ICLR 2023

We present a subset selection algorithm designed to work with arbitrary model families in a practical batch setting. In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i.e. further train model weights) once a large enough batch of examples is selected. Our algorithm, IWeS, selects examples by importance sampling where the sampling probability assigned to each example is based on the entropy of models trained on previously selected batches. IWeS admits significant performance improvement compared to other subset selection algorithms for seven publicly available datasets. Additionally, it is competitive in an active learning setting, where the label information is not available at selection time. We also provide an initial theoretical analysis to support our importance weighting approach, proving generalization and sampling rate bounds., Comment: ICLR 2023