Representation learning from unlabeled data has been extensively studied in statistics, data science and signal processing with a rich literature on techniques for dimension reduction, compression, multi-dimensional scaling among others. However, current deep learning models use new principles for unsupervised representation learning that cannot be easily analyzed using classical theories. For example, visual foundation models have found tremendous success using self-supervision or denoising/masked autoencoders, which effectively learn representations from massive amounts of unlabeled data. However, it remains difficult to characterize the representations learned by these models and to explain why they perform well for diverse prediction tasks or show emergent behavior. To answer these questions, one needs to combine mathematical tools from statistics and optimization. This paper provides an overview of recent theoretical advances in representation learning from unlabeled data and mentions our contributions in this direction.

Search-based software engineering (SBSE), which integrates metaheuristic search techniques with software engineering, has been an active area of research for about 25 years. It has been applied to solve numerous problems across the entire software engineering lifecycle and has demonstrated its versatility in multiple domains. With recent advances in AI, particularly the emergence of foundation models (FMs) such as large language models (LLMs), the evolution of SBSE alongside these models remains undetermined. In this window of opportunity, we present a research roadmap that articulates the current landscape of SBSE in relation to FMs, identifies open challenges, and outlines potential research directions to advance SBSE through its integration and interplay with FMs. Specifically, we analyze five core aspects: leveraging FMs for SBSE design, applying FMs to complement SBSE in SE problems, employing SBSE to address FM challenges, adapting SBSE practices for FMs tailored to SE activities, and exploring the synergistic potential between SBSE and FMs. Furthermore, we present a forward-thinking perspective that envisions the future of SBSE in the era of FMs, highlighting promising research opportunities to address challenges in emerging domains.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper looks at differentially private algorithms for a generic maximization problem (private argmax might be a good name). Given a collection of K of items, and a data set D of n individuals, and a score function f that assigns each item i a data-based score f(i;D), the goal is to find an item i with approximately maximal score, while preserving differential privacy. This private argmax has proven to be a fundamental problem in the theory of private data analysis. It was first formulated by McSherry and Talwar (2007), who proposed the exponential mechanism to solve it.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes an incremental but very sensible and practical modification to'curriculum learning'. Given a partition of the training examples into classes, they propose an additional regularising term (and an additional parameter) to ensure that the'easy' examples selected during learning are spread across the classes, and not from one class. The partition into classes can come from a clustering algorithm, or from a priori knowledge. The idea is straightforward and sensible, and the authors propose an algorithm that looks efficient and correct.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper presents a VB method for learning nonlinear state-space models using sparse GPs to model the nonlinear state transition and observation mappings. The proposed method looks very good and efficient, but the empirical evaluation is relatively weak. Quality: The paper appears technically sound, save one minor problem listed below. The method is based on existing solid principles with VB-based sparse GPs, stochastic variational inference and sequential Monte Carlo.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. In particle filtering, the resampling step is a synchronous operation: one needs all the particles before computing the normalised weights (since the denominator is the sum of all the weights), and then resample. The reviewed paper propose an asynchronous resampling mechanism, where the number of children of particle k depends only the weights of particles 1 to k. The proposed idea is quite straightforward, but still interesting and potentially very useful. What is a bit lacking in the current version is some motivation for an asynchronous implementation of particle filtering.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes projecting the parameters of an MRF onto the set of fast-mixing parameters: parameters for which MCMC quickly converges to the true distribution. The authors introduce a Euclidean projection operator that implements this property, but note that it can be difficult to apply. They then smooth it by requiring the projection to be close to an additional matrix input. This is sufficient for many cases, but can be applied repeatedly when the true Euclidean projection is required.

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1350" "Title:","Distributed Balanced Clustering via Mapping Coresets" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes coreset approach for balanced clustering. The paper is not clearly written and lacks intuition and motivation. Although it refers to clustering, what is exactly the clustering objective function? The problem defined in Sec 4 is slightly modified k-median problem, what does it has to do with cluster balance?

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors propose a novel method for image representation called Convolutional Kernel Methods. It is different from similar methods in that it is not designed for explicitly reconstructing then data, or for classifying it. The patch-map and gradient-map approaches obtain quite competitive numbers on MNIST, and reasonable numbers (if not quite state of the art) on CIFAR-10 and STL-10. The Gabor filters obtained on the natural image patches are quite interesting too.