The reviewers found that this paper was useful for the field, offering a new method for aligning multi-site fMRI data, with some disagreement. One of the main concerns was about the clarity of the paper which greatly impacts its usefulness. Please improve the quality of the writing for the final draft. There is a major typo in the paper: everywhere XX T is mentioned, I think you mean X TX (the identify matrices are also wrongly subscripted). In fact R1's comment is right, XX T is likely not singular given V T.

Deep learning methods have demonstrated strong performance in objection tasks; however, their ability to learn domain-specific applications with limited training data remains a significant challenge. Transfer learning techniques address this issue by leveraging knowledge from pre-training on related datasets, enabling faster and more efficient learning for new tasks. Finding the right dataset for pre-training can play a critical role in determining the success of transfer learning and overall model performance. In this paper, we investigate the impact of pre-training a YOLOv8n model on seven distinct datasets, evaluating their effectiveness when transferred to the task of polyp detection. We compare whether large, general-purpose datasets with diverse objects outperform niche datasets with characteristics similar to polyps. In addition, we assess the influence of the size of the dataset on the efficacy of transfer learning. Experiments on the polyp datasets show that models pre-trained on relevant datasets consistently outperform those trained from scratch, highlighting the benefit of pre-training on datasets with shared domain-specific features.

A central challenge in transfer learning is designing algorithms that can quickly adapt and generalize to new tasks without retraining. Yet, the conditions of when and how algorithms can effectively transfer to new tasks is poorly characterized. We introduce a geometric characterization of transfer in Hilbert spaces and define three types of inductive transfer: interpolation within the convex hull, extrapolation to the linear span, and extrapolation outside the span. We propose a method grounded in the theory of function encoders to achieve all three types of transfer. Specifically, we introduce a novel training scheme for function encoders using least-squares optimization, prove a universal approximation theorem for function encoders, and provide a comprehensive comparison with existing approaches such as transformers and meta-learning on four diverse benchmarks. Our experiments demonstrate that the function encoder outperforms state-of-the-art methods on four benchmark tasks and on all three types of transfer.

Surrogate models provide efficient alternatives to computationally demanding real-world processes but often require large datasets for effective training. A promising solution to this limitation is the transfer of pre-trained surrogate models to new tasks. Previous studies have investigated the transfer of differentiable and non-differentiable surrogate models, typically assuming an affine transformation between the source and target functions. This paper extends previous research by addressing a broader range of transformations, including linear and nonlinear variations. Specifically, we consider the combination of an unknown input warping, such as one modelled by the beta cumulative distribution function, with an unspecified affine transformation. Our approach achieves transfer learning by employing a limited number of data points from the target task to optimize these transformations, minimizing empirical loss on the transfer dataset. We validate the proposed method on the widely used Black-Box Optimization Benchmark (BBOB) testbed and a real-world transfer learning task from the automobile industry. The results underscore the significant advantages of the approach, revealing that the transferred surrogate significantly outperforms both the original surrogate and the one built from scratch using the transfer dataset, particularly in data-scarce scenarios.

Dynamic pricing strategies are crucial for firms to maximize revenue by adjusting prices based on market conditions and customer characteristics. However, designing optimal pricing strategies becomes challenging when historical data are limited, as is often the case when launching new products or entering new markets. One promising approach to overcome this limitation is to leverage information from related products or markets to inform the focal pricing decisions. In this paper, we explore transfer learning for nonparametric contextual dynamic pricing under a covariate shift model, where the marginal distributions of covariates differ between source and target domains while the reward functions remain the same. We propose a novel Transfer Learning for Dynamic Pricing (TLDP) algorithm that can effectively leverage pre-collected data from a source domain to enhance pricing decisions in the target domain. The regret upper bound of TLDP is established under a simple Lipschitz condition on the reward function. To establish the optimality of TLDP, we further derive a matching minimax lower bound, which includes the target-only scenario as a special case and is presented for the first time in the literature. Extensive numerical experiments validate our approach, demonstrating its superiority over existing methods and highlighting its practical utility in real-world applications.

Positives The paper is well-written and includes a through literature review. The following paper is also very relevant to the submission: Shrivastava, Ashish, et al. "Learning from simulated and unsupervised images through adversarial training." Novelty of the method over [44] is not major. Still, I believe no one has shown that computing flow on simulated data and using it for training improves over RGB only (although the improvement is quite marginal). Simulation pipeline proposed in the paper seems to be quite useful.

After reviewer discussion and rebuttal this paper received three acceptance recommendations. R1 and R2 are more positive about the paper and acknoweldge the contribution. R3 points out that the impact of using just flow and no person and camera motion is limited. Please consider the post-rebuttal portion of the review to include in a final revision. The method, approach and quality of the paper are high as acknowledged by all reviewers.

While the presented model can be posed as a transfer learning problem. This paper is more about concept drift. Therefore, the title Transfer learning via l1 Regularization is a bit too broad and can be misleading for some readers. However, Lasso is not considered as a state-of-the-art (SOTA) for concept drift and transfer learning. Lasso is designed for neither of these problem. On the other hand, there are many other methods for concept drift and transfer learning, with some discussed in the Related Work section but none is compared against in the experiment.

Though the original reviews were on the low side, after the discussion it was agreed that the paper should be primarily viewed as a *theory* paper, giving provable guarantees about a particular kind of transfer/concept drift in linear regression settings -- allowing *sparse* changes in features. On the other hand, it's also agreed that the paper *oversells* its impact in the introductory portions and the rhetoric should be somewhat toned down -- in particular, we ask the authors to point out that the main contribution is an algorithm with *theoretical guarantees* that isn't being proposed (at least as of the writing of the paper) as a competitive method with existing heuristics/algorithms.

The reviewer thinks that the novelty of this paper is not enough. The title of this paper is "Catastrophic Forgetting Meets Negative Transfer". However, the part that deals with catastrophic forgetting only uses the previous methods, and the formula only extends the proposed BSS regularization to the previous methods. There are also no ablation studies to verify the effectiveness of the two parts, i.e., catastrophic forgetting part and negative transfer part. So aligning all weight parameters indiscriminately to the initial pre-trained values is risky to negative transfer."