Lower bound on regret: Assuming you mean Theorem 3 here - the theorem is correct as stated. We however use the correct defn. in all of our proofs. We mean Lipschitz continuity, as we want close-by models to imply the solution values are close. The use of this term is meant to follow the notation in Bottou et. It is defined in the formal statement of Theorem 2 (Theorem 5 in the appendix).

We thank all reviewers for their thorough reading of our paper and for their detailed and insightful reviews. We answer specific questions below and will incorporate all feedback. Can you give more details on the method runtime? Table 2 shows average MIP runtimes given different architectures and solvers. MIP), and a policy iteration may take up to an hour in parallel.

In many reinforcement learning (RL) applications, incorporating heuristic rewards alongside the task reward is crucial for achieving desirable performance. Heuristics encode prior human knowledge about how a task should be done, providing valuable hints for RL algorithms. However, such hints may not be optimal, limiting the performance of learned policies. The currently established way of using heuristics is to modify the heuristic reward in a manner that ensures that the optimal policy learned with it remains the same as the optimal policy for the task reward (i.e., optimal policy invariance). However, these methods often fail in practical scenarios with limited training data. We found that while optimal policy invariance ensures convergence to the best policy based on task rewards, it doesn't guarantee better performance than policies trained with biased heuristics under a finite data regime, which is impractical. In this paper, we introduce a new principle tailored for finite data settings. Instead of enforcing optimal policy invariance, we train a policy that combines task and heuristic rewards and ensures it outperforms the heuristic-trained policy. As such, we prevent policies from merely exploiting heuristic rewards without improving the task reward.

Instruction tuning is a supervised fine-tuning approach that significantly improves the ability of large language models (LLMs) to follow human instructions. For programming tasks, most models are finetuned with costly human-annotated instruction-response pairs or those generated by large, proprietary LLMs, which may not be permitted. We propose SelfCodeAlign, the first fully transparent and permissive pipeline for self-aligning code LLMs without extensive human annotations or distillation. SelfCodeAlign employs the same base model for inference throughout the data generation process. It first extracts diverse coding concepts from high-quality seed snippets to generate new tasks.

We propose ACProp (Asynchronous-centering-Prop), an adaptive optimizer which combines centering of second momentum and asynchronous update (e.g. for $t$-th update, denominator uses information up to step $t-1$, while numerator uses gradient at $t$-th step). ACProp has both strong theoretical properties and empirical performance. With the example by Reddi et al. (2018), we show that asynchronous optimizers (e.g. AdaShift, ACProp) have weaker convergence condition than synchronous optimizers (e.g. Adam, RMSProp, AdaBelief); within asynchronous optimizers, we show that centering of second momentum further weakens the convergence condition. We demonstrate that ACProp has a convergence rate of $O(\frac{1}{\sqrt{T}})$ for the stochastic non-convex case, which matches the oracle rate and outperforms the $O(\frac{logT}{\sqrt{T}})$ rate of RMSProp and Adam. We validate ACProp in extensive empirical studies: ACProp outperforms both SGD and other adaptive optimizers in image classification with CNN, and outperforms well-tuned adaptive optimizers in the training of various GAN models, reinforcement learning and transformers. To sum up, ACProp has good theoretical properties including weak convergence condition and optimal convergence rate, and strong empirical performance including good generalization like SGD and training stability like Adam.

Learning from AI feedback (LAIF) is a popular paradigm for improving the instruction-following abilities of powerful pre-trained language models. LAIF first performs supervised fine-tuning (SFT) using demonstrations from a teacher model and then further fine-tunes the model with reinforcement learning (RL) or direct preference optimization (DPO), using feedback from a critic model. While recent popular open-source models have demonstrated substantial improvements in performance from the RL step, in this paper we question whether the complexity of this RL step is truly warranted for AI feedback. We show that the improvements of the RL step are virtually entirely due to the widespread practice of using a weaker teacher model (e.g. GPT-3.5) for SFT data collection than the critic (e.g., GPT-4) used for AI feedback generation. Specifically, we show that simple supervised fine-tuning with GPT-4 as the teacher outperforms existing LAIF pipelines. More generally, we find that the gains from LAIF vary substantially across base model families, test-time evaluation protocols, and critic models. Finally, we provide a mechanistic explanation for when SFT may outperform the full two-step LAIF pipeline as well as suggestions for making LAIF maximally useful in practice.

In this paper we tackle the problem of Generalized Category Discovery (GCD). Specifically, given a dataset with labelled and unlabelled images, the task is to cluster all images in the unlabelled subset, whether or not they belong to the labelled categories. Our first contribution is to recognise that most existing GCD benchmarks only contain labels for a single clustering of the data, making it difficult to ascertain whether models are leveraging the available labels to solve the GCD task, or simply solving an unsupervised clustering problem. As such, we present a synthetic dataset, named'Clevr-4', for category discovery. Clevr-4 contains four equally valid partitions of the data, i.e based on object'shape', 'texture' or'color' or'count'.

This paper studies how to design abstractions of large-scale combinatorial optimization problems that can leverage existing state-of-the-art solvers in general-purpose ways, and that are amenable to data-driven design. The goal is to arrive at new approaches that can reliably outperform existing solvers in wall-clock time. We focus on solving integer programs and ground our approach in the large neighborhood search (LNS) paradigm, which iteratively chooses a subset of variables to optimize while leaving the remainder fixed. The appeal of LNS is that it can easily use any existing solver as a subroutine, and thus can inherit the benefits of carefully engineered heuristic approaches and their software implementations. We also show that one can learn a good neighborhood selector from training data. Through an extensive empirical validation, we demonstrate that our LNS framework can significantly outperform, in wall-clock time, compared to state-of-the-art commercial solvers such as Gurobi.

Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations that are consistent under both data augmentations and adversarial perturbations. Our approach leverages a recent contrastive learning framework, which learns representations by maximizing feature consistency under differently augmented views. This fits particularly well with the goal of adversarial robustness, as one cause of adversarial fragility is the lack of feature invariance, i.e., small input perturbations can result in undesirable large changes in features or even predicted labels. We explore various options to formulate the contrastive task, and demonstrate that by injecting adversarial perturbations, contrastive pre-training can lead to models that are both label-efficient and robust. We empirically evaluate the proposed Adversarial Contrastive Learning (ACL) and show it can consistently outperform existing methods. For example on the CIFAR-10 dataset, ACL outperforms the previous state-of-the-art unsupervised robust pre-training approach by 2.99% on robust accuracy and 2.14% on standard accuracy. We further demonstrate that ACL pre-training can improve semi-supervised adversarial training, even when only a few labeled examples are available.

Driven by the progress of large-scale pre-training, parameter-efficient transfer learning has gained immense popularity across different subfields of Artificial Intelligence. The core is to adapt the model to downstream tasks with only a small set of parameters. Recently, researchers have leveraged such proven techniques in multimodal tasks and achieve promising results. However, two critical issues remain unresolved: how to further reduce the complexity with lightweight design and how to boost alignment between modalities under extremely low parameters. In this paper, we propose A gracefUl pRompt framewOrk for cRoss-modal trAnsfer (AURORA) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0.1M trainable parameters to implement the multimodal parameter-efficient tuning, which explores the low intrinsic dimension with only 0.04% parameters of the pre-trained model. Then, for better modality alignment, we propose the Informative Context Enhancement and Gated Query Transformation module under extremely few parameters scenes. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach.