Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity

While deep learning (DL) models are state-of-the-art in text and image domains, they have not yet consistently outperformed Gradient Boosted Decision Trees (GBDTs) on tabular Learning-To-Rank (LTR) problems. Most of the recent performance gains attained by DL models in text and image tasks have used unsupervised pretraining, which exploits orders of magnitude more unlabeled data than labeled data. To the best of our knowledge, unsupervised pretraining has not been applied to the LTR problem, which often produces vast amounts of unlabeled data. In this work, we study whether unsupervised pretraining can improve LTR performance over GBDTs and other non-pretrained models. Using simple design choices--including SimCLR-Rank, our ranking-specific modification of SimCLR (an unsupervised pretraining method for images)--we produce pretrained deep learning models that soundly outperform GBDTs (and other non-pretrained models) in the case where labeled data is vastly outnumbered by unlabeled data. We also show that pretrained models also often achieve significantly better robustness than non-pretrained models (GBDTs or DL models) in ranking outlier data.

Logarithmic Bayes Regret Bounds

We derive the first finite-time logarithmic regret bounds for Bayesian bandits. For Gaussian bandits, we obtain a $O(c_h \log^2 n)$ bound, where $c_h$ is a prior-dependent constant. This matches the asymptotic lower bound of Lai (1987). Our proofs mark a technical departure from prior works, and are simple and general. To show generality, we apply our technique to linear bandits. Our bounds shed light on the value of the prior in the Bayesian setting, both in the objective and as a side information given to the learner. They significantly improve the $\tilde{O}(\sqrt{n})$ bounds, that despite the existing lower bounds, have become standard in the literature.

Understanding the Effectiveness of Early Weight Averaging for Training Large Language Models

Training LLMs is expensive, and recent evidence indicates training all the way to convergence is inefficient. In this paper, we investigate the ability of a simple idea, checkpoint averaging along the trajectory of a training run to improve the quality of models before they have converged. This approach incurs no extra cost during training or inference. Specifically, we analyze the training trajectories of Pythia LLMs with 1 to 12 billion parameters and demonstrate that, particularly during the early to mid stages of training, this idea accelerates convergence and improves both test and zero-shot generalization. Loss spikes are a well recognized problem in LLM training; in our analysis we encountered two instances of this in the underlying trajectories, and both instances were mitigated by our averaging. For a 6.9B parameter LLM, for example, our early weight averaging recipe can save upto 4200 hours of GPU time, which corresponds to significant savings in cloud compute costs.

Understanding Self-Distillation in the Presence of Label Noise

Self-distillation (SD) is the process of first training a \enquote{teacher} model and then using its predictions to train a \enquote{student} model with the \textit{same} architecture. Specifically, the student's objective function is $\big(\xi*\ell(\text{teacher's predictions}, \text{ student's predictions}) + (1-\xi)*\ell(\text{given labels}, \text{ student's predictions})\big)$, where $\ell$ is some loss function and $\xi$ is some parameter $\in [0,1]$. Empirically, SD has been observed to provide performance gains in several settings. In this paper, we theoretically characterize the effect of SD in two supervised learning problems with \textit{noisy labels}. We first analyze SD for regularized linear regression and show that in the high label noise regime, the optimal value of $\xi$ that minimizes the expected error in estimating the ground truth parameter is surprisingly greater than 1. Empirically, we show that $\xi > 1$ works better than $\xi \leq 1$ even with the cross-entropy loss for several classification datasets when 50\% or 30\% of the labels are corrupted. Further, we quantify when optimal SD is better than optimal regularization. Next, we analyze SD in the case of logistic regression for binary classification with random label corruption and quantify the range of label corruption in which the student outperforms the teacher in terms of accuracy. To our knowledge, this is the first result of its kind for the cross-entropy loss.

Latent Variable Representation for Reinforcement Learning

Deep latent variable models have achieved significant empirical successes in model-based reinforcement learning (RL) due to their expressiveness in modeling complex transition dynamics. On the other hand, it remains unclear theoretically and empirically how latent variable models may facilitate learning, planning, and exploration to improve the sample efficiency of RL. In this paper, we provide a representation view of the latent variable models for state-action value functions, which allows both tractable variational learning algorithm and effective implementation of the optimism/pessimism principle in the face of uncertainty for exploration. In particular, we propose a computationally efficient planning algorithm with UCB exploration by incorporating kernel embeddings of latent variable models. Theoretically, we establish the sample complexity of the proposed approach in the online and offline settings. Empirically, we demonstrate superior performance over current state-of-the-art algorithms across various benchmarks.

Bayesian Fixed-Budget Best-Arm Identification

Fixed-budget best-arm identification (BAI) is a bandit problem where the learning agent maximizes the probability of identifying the optimal arm after a fixed number of observations. In this work, we initiate the study of this problem in the Bayesian setting. We propose a Bayesian elimination algorithm and derive an upper bound on the probability that it fails to identify the optimal arm. The bound reflects the quality of the prior and is the first such bound in this setting. We prove it using a frequentist-like argument, where we carry the prior through, and then integrate out the random bandit instance at the end. Our upper bound asymptotically matches a newly established lower bound for $2$ arms. Our experimental results show that Bayesian elimination is superior to frequentist methods and competitive with the state-of-the-art Bayesian algorithms that have no guarantees in our setting.

Toward Understanding Privileged Features Distillation in Learning-to-Rank

In learning-to-rank problems, a privileged feature is one that is available during model training, but not available at test time. Such features naturally arise in merchandised recommendation systems; for instance, "user clicked this item" as a feature is predictive of "user purchased this item" in the offline data, but is clearly not available during online serving. Another source of privileged features is those that are too expensive to compute online but feasible to be added offline. Privileged features distillation (PFD) refers to a natural idea: train a "teacher" model using all features (including privileged ones) and then use it to train a "student" model that does not use the privileged features. In this paper, we first study PFD empirically on three public ranking datasets and an industrial-scale ranking problem derived from Amazon's logs. We show that PFD outperforms several baselines (no-distillation, pretraining-finetuning, self-distillation, and generalized distillation) on all these datasets. Next, we analyze why and when PFD performs well via both empirical ablation studies and theoretical analysis for linear models. Both investigations uncover an interesting non-monotone behavior: as the predictive power of a privileged feature increases, the performance of the resulting student model initially increases but then decreases. We show the reason for the later decreasing performance is that a very predictive privileged teacher produces predictions with high variance, which lead to high variance student estimates and inferior testing performance.

On the Value of Behavioral Representations for Dense Retrieval

We consider text retrieval within dense representational space in real-world settings such as e-commerce search where (a) document popularity and (b) diversity of queries associated with a document have a skewed distribution. Most of the contemporary dense retrieval literature presents two shortcomings in these settings. (1) They learn an almost equal number of representations per document, agnostic to the fact that a few head documents are disproportionately more critical to achieving a good retrieval performance. (ii) They learn purely semantic document representations inferred from intrinsic document characteristics which may not contain adequate information to determine the queries for which the document is relevant--especially when the document is short. We propose to overcome these limitations by augmenting semantic document representations learned by bi-encoders with behavioral document representations learned by our proposed approach MVG. To do so, MVG (1) determines how to divide the total budget for behavioral representations by drawing a connection to the Pitman-Yor process, and (2) simply clusters the queries related to a given document (based on user behavior) within the representational space learned by a base bi-encoder, and treats the cluster centers as its behavioral representations. Our central contribution is the finding such a simple intuitive light-weight approach leads to substantial gains in key first-stage retrieval metrics by incurring only a marginal memory overhead. We establish this via extensive experiments over three large public datasets comparing several single-vector and multi-vector bi-encoders, a proprietary e-commerce search dataset compared to production-quality bi-encoder, and an A/B test.

Beyond Uniform Lipschitz Condition in Differentially Private Optimization

Most prior convergence results on differentially private stochastic gradient descent (DP-SGD) are derived under the simplistic assumption of uniform Lipschitzness, i.e., the per-sample gradients are uniformly bounded. This assumption is unrealistic in many problems, e.g., linear regression with Gaussian data. We relax uniform Lipschitzness by instead assuming that the per-sample gradients have \textit{sample-dependent} upper bounds, i.e., per-sample Lipschitz constants, which themselves may be unbounded. We derive new convergence results for DP-SGD on both convex and nonconvex functions when the per-sample Lipschitz constants have bounded moments. Furthermore, we provide principled guidance on choosing the clip norm in DP-SGD for convex settings satisfying our relaxed version of Lipschitzness, without making distributional assumptions on the Lipschitz constants. We verify the effectiveness of our recommendation via experiments on benchmarking datasets.

Positive Unlabeled Contrastive Learning

Self-supervised pretraining on unlabeled data followed by supervised finetuning on labeled data is a popular paradigm for learning from limited labeled examples. In this paper, we investigate and extend this paradigm to the classical positive unlabeled (PU) setting - the weakly supervised task of learning a binary classifier only using a few labeled positive examples and a set of unlabeled samples. We propose a novel PU learning objective positive unlabeled Noise Contrastive Estimation (puNCE) that leverages the available explicit (from labeled samples) and implicit (from unlabeled samples) supervision to learn useful representations from positive unlabeled input data. The underlying idea is to assign each training sample an individual weight; labeled positives are given unit weight; unlabeled samples are duplicated, one copy is labeled positive and the other as negative with weights $\pi$ and $(1-\pi)$ where $\pi$ denotes the class prior. Extensive experiments across vision and natural language tasks reveal that puNCE consistently improves over existing unsupervised and supervised contrastive baselines under limited supervision.