The maximal correlations and correlation functions are then used to predict the class for the target sample. The evaluation is done on 3 datasets (CIFAR100, Stanford Dogs, and Tiny Imagenet). The proposed MCW method is compared with SVM trained on output of the penultimate layer. For all the datasets, the Multi-Source MCW shows significant advantage especially when there are few samples.

The paper presents a very interesting and efficient technique for transfer learning which is validated on image classification data. The three reviewers agreed on the quality and siginficance of the contributions. I recommend acceptance as a poster presentation.

Summary: This paper considers few-shot classification and seeks to make use of the unlabeled query data during few-shot classification by training on it with a meta-learned critic loss. The algorithm builds on top of MAML, and has two stages. In the first stage, the model is adapted via gradient descent on the labeled support set. In the second stage, the model is further adapted via a meta-learned critic loss that is a function of a featurization of the model parameters and the unlabeled query set. Originality: The proposed approach strikes me as quite similar to One-Shot Imitation Learning by Domain-Adaptive Meta-Learning (Yu et al. 2018).

The reviewers agreed that this submission makes an interesting and novel contribution to NeurIPS. I strongly encourage the authors to address the remaining comments of reviewers 3 and 6, to clarify the test batch size, improve figure 2, and add citations.

The field of quantum computing is generating significant anticipation within the scientific and industrial communities due to its potential to revolutionize computing paradigms. Recognizing this potential, this paper explores the integration of transfer of knowledge techniques, traditionally used in classical artificial intelligence, into quantum computing. We present a comprehensive classification of the transfer models, focusing on Transfer Learning and Transfer Optimization. Additionally, we analyze relevant schemes in quantum computing that can benefit from knowledge sharing, and we delve into the potential synergies, supported by theoretical insights and initial experimental results. Our findings suggest that leveraging the transfer of knowledge can enhance the efficiency and effectiveness of quantum algorithms, particularly in the context of hybrid solvers. This approach not only accelerates the optimization process but also reduces the computational burden on quantum processors, making it a valuable tool for advancing quantum computing technologies.

The manuscript presents a set of diverse protein prediction tasks, with the purpose of establishing a benchmark for testing representation/transfer learning on protein sequence data. In addition, it establishes a strong baseline for the field by implementing a range of different standard sequence models, and demonstrating their performance on a benchmark set. I expect both the benchmark set, and the results reported in this paper to have a substantial impact on the community. Below are some comments and suggestions for changes Page 3. Since the goal is to "ensure that no test proteins are closely related to train proteins", it would be informative if the authors could state the expected (or maximum) sequence identity between PFAM families. Wouldn't it have made sense to do the split at the clan level, to reduce the chance of information leakage between families within the same superfamily? About task 2: much of recent progress in protein structure prediction comes from prediction of distance distributions rather than a simple binary classification of contact presence.

Weaknesses: -The cost function formulation is similar to previous work of [17] and [43]. The adversarial objective minimized is based on prior work of [17] and [43]. Given this, the proposed approach does not offer significant technical novelty. However, the experiments are based on sim-to-sim evaluation where there are two simulator for a task and one of them is called'real'. I do not see such characterization as acceptable.

Summary: This paper proposes a new technique for learning to transfer optimal policies obtained from a simulator to a real world environment. The only difference between sim and real is in the state transition probabilities. The main idea consists in learning an action grounding function that maps state-actions learned in simulation to modified actions that are executed in the real system. The authors notice that this problem is similar to a variant of imitation learning, where the imitator learns to match state trajectories (where the actions are unknown) demonstrated by an expert. Experiments on MuJoCO where the "real" environment is obtained by modifying physical properties (such as mass and friction) from their values in simulation.

Normally when comparing different models/algorithms, effort should be taken to find the best performing parameters (or more generally most suitable formalisations) for each model.

The paper proposes an improvement of popular'successor representation' approaches in reinforcement learning via a mechanism for maintaining and quickly updating a distribution over multiple successor maps. This innovation enables the model to adapt better to environmental changes such as different goals or reward structures. All three reviewers agree that this is a strong paper that should be accepted. I see no reason to contradict their opinion. While the reviewers were very positive, they did point out issues of clarity in the exposition, and we would like to remind the authors that their paper will reach a wider audience if they can make the presentation and explanation as clear and simple as possible in the camera ready version.