Fine-tuning and inference with large Language Models (LM) are generally known to be expensive. Parameter-efficient fine-tuning over pretrained LMs reduces training memory by updating a small number of LM parameters but does not improve inference efficiency. Structured pruning improves LM inference efficiency by removing consistent parameter blocks, yet often increases training memory and time. To improve both training and inference efficiency, we introduce APT that adaptively prunes and tunes parameters for the LMs. At the early stage of fine-tuning, APT dynamically adds salient tuning parameters for fast and accurate convergence while discarding unimportant parameters for efficiency. Compared to baselines, our experiments show that APT maintains up to 98% task performance when pruning RoBERTa and T5 models with 40% parameters left while keeping 86.4% LLaMA models' performance with 70% parameters remained. Furthermore, APT speeds up LMs fine-tuning by up to 8x and reduces large LMs memory training footprint by up to 70%.

Image segmentation is a clustering task whereby each pixel is assigned a cluster label. Remote sensing data usually consists of multiple bands of spectral images in which there exist semantically meaningful land cover subregions, co-registered with other source data such as LIDAR (LIght Detection And Ranging) data, where available. This suggests that, in order to account for spatial correlation between pixels, a feature vector associated with each pixel may be a vectorized tensor representing the multiple bands and a local patch as appropriate. Similarly, multiple types of texture features based on a pixel's local patch would also be beneficial for encoding locally statistical information and spatial variations, without necessarily labelling pixel-wise a large amount of ground truth, then training a supervised model, which is sometimes impractical. In this work, by resorting to label only a small quantity of pixels, a new semi-supervised segmentation approach is proposed. Initially, over all pixels, an image data matrix is created in high dimensional feature space. Then, t-SNE projects the high dimensional data onto 3D embedding. By using radial basis functions as input features, which use the labelled data samples as centres, to pair with the output class labels, a modified canonical correlation analysis algorithm, referred to as RBF-CCA, is introduced which learns the associated projection matrix via the small labelled data set. The associated canonical variables, obtained for the full image, are applied by k-means clustering algorithm. The proposed semi-supervised RBF-CCA algorithm has been implemented on several remotely sensed multispectral images, demonstrating excellent segmentation results.

Over-the-air federated learning (OTA-FL) provides bandwidth-efficient learning by leveraging the inherent superposition property of wireless channels. Personalized federated learning balances performance for users with diverse datasets, addressing real-life data heterogeneity. We propose the first personalized OTA-FL scheme through multi-task learning, assisted by personal reconfigurable intelligent surfaces (RIS) for each user. We take a cross-layer approach that optimizes communication and computation resources for global and personalized tasks in time-varying channels with imperfect channel state information, using multi-task learning for non-i.i.d data. Our PROAR-PFed algorithm adaptively designs power, local iterations, and RIS configurations. We present convergence analysis for non-convex objectives and demonstrate that PROAR-PFed outperforms state-of-the-art on the Fashion-MNIST dataset.

While large language models (LLMs) are still being adopted to new domains and utilized in novel applications, we are experiencing an influx of the new generation of foundation models, namely multi-modal large language models (MLLMs). These models integrate verbal and visual information, opening new possibilities to demonstrate more complex reasoning abilities at the intersection of the two modalities. However, despite the revolutionizing prospect of MLLMs, our understanding of their reasoning abilities is limited. In this study, we assess the nonverbal abstract reasoning abilities of open-source and closed-source MLLMs using variations of Raven's Progressive Matrices. Our experiments expose the difficulty of solving such problems while showcasing the immense gap between open-source and closed-source models. We also reveal critical shortcomings with individual visual and textual modules, subjecting the models to low-performance ceilings. Finally, to improve MLLMs' performance, we experiment with various methods, such as Chain-of-Thought prompting, resulting in a significant (up to 100%) boost in performance.

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by generating synthetic preference data, thereby augmenting the training dataset with on-policy, high-quality preference pairs. Motivated by the promising results of Best-of-N sampling strategies in language model training, we extend their application to reward model training. This results in a self-training strategy to generate preference pairs by selecting the best and worst candidates in a pool of responses to a given query. Empirically, we find that this approach improves the performance of any reward model, with an effect comparable to the addition of a similar quantity of human preference data. This work opens up new avenues of research for improving RLHF for language model alignment, by offering synthetic preference generation as a solution to reward modeling challenges.

The study of generalization properties of stochastic optimization algorithms has been at the heart of contemporary machine learning research. While in the more classical frameworks studies largely focused on the learning problem (e.g., Alon et al., 1997; Blumer et al., 1989), in the past decade it has become clear that in modern scenarios the particular algorithm used to learn the model plays a vital role in its generalization performance. As a prominent example, heavily over-parameterized deep neural networks trained by first order methods output models that generalize well, despite the fact that an arbitrarily chosen Empirical Risk Minimizer (ERM) may perform poorly (Zhang et al., 2017; Neyshabur et al., 2014, 2017). The present paper aims at understanding the generalization behavior of gradient methods, specifically in connection with the problem dimension, in the fundamental Stochastic Convex Optimization (SCO) learning setup; a well studied, theoretical framework widely used to study stochastic optimization algorithms. The seminal work of Shalev-Shwartz et al. (2010) was the first to show that uniform convergence, the canonical condition for generalization in statistical learning (e.g., Vapnik, 1971; Bartlett and Mendelson, 2002) may not hold in high-dimensional SCO: they demonstrated learning problems where there exist certain ERMs that overfit the training data (i.e., exhibit large population risk), while models produced by e.g., Stochastic Gradient Descent (SGD) or regularized empirical risk minimization generalize well. The construction presented by Shalev-Shwartz et al. (2010), however, featured a learning problem with dimension exponential in the number of training

Conformal risk control (CRC) is a recently proposed technique that applies post-hoc to a conventional point predictor to provide calibration guarantees. Generalizing conformal prediction (CP), with CRC, calibration is ensured for a set predictor that is extracted from the point predictor to control a risk function such as the probability of miscoverage or the false negative rate. The original CRC requires the available data set to be split between training and validation data sets. This can be problematic when data availability is limited, resulting in inefficient set predictors. In this paper, a novel CRC method is introduced that is based on cross-validation, rather than on validation as the original CRC. The proposed cross-validation CRC (CV-CRC) extends a version of the jackknife-minmax from CP to CRC, allowing for the control of a broader range of risk functions. CV-CRC is proved to offer theoretical guarantees on the average risk of the set predictor. Furthermore, numerical experiments show that CV-CRC can reduce the average set size with respect to CRC when the available data are limited.

The advancement of machine learning and symbolic approaches have underscored their strengths and weaknesses in Natural Language Processing (NLP). While machine learning approaches are powerful in identifying patterns in data, they often fall short in learning commonsense and the factual knowledge required for the NLP tasks. Meanwhile, the symbolic methods excel in representing knowledge-rich data. However, they struggle to adapt dynamic data and generalize the knowledge. Bridging these two paradigms through hybrid approaches enables the alleviation of weaknesses in both while preserving their strengths. Recent studies extol the virtues of this union, showcasing promising results in a wide range of NLP tasks. In this paper, we present an overview of hybrid approaches used for NLP. Specifically, we delve into the state-of-the-art hybrid approaches used for a broad spectrum of NLP tasks requiring natural language understanding, generation, and reasoning. Furthermore, we discuss the existing resources available for hybrid approaches for NLP along with the challenges, offering a roadmap for future directions.

The pursue of what are properties that can be identified to permit an automated reasoning program to generate and find new and interesting theorems is an interesting research goal (pun intended). The automatic discovery of new theorems is a goal in itself, and it has been addressed in specific areas, with different methods. The separation of the "weeds", uninteresting, trivial facts, from the "wheat", new and interesting facts, is much harder, but is also being addressed by different authors using different approaches. In this paper we will focus on geometry. We present and discuss different approaches for the automatic discovery of geometric theorems (and properties), and different metrics to find the interesting theorems among all those that were generated. After this description we will introduce the first result of this article: an undecidability result proving that having an algorithmic procedure that decides for every possible Turing Machine that produces theorems, whether it is able to produce also interesting theorems, is an undecidable problem. Consequently, we will argue that judging whether a theorem prover is able to produce interesting theorems remains a non deterministic task, at best a task to be addressed by program based in an algorithm guided by heuristics criteria. Therefore, as a human, to satisfy this task two things are necessary: an expert survey that sheds light on what a theorem prover/finder of interesting geometric theorems is, and - to enable this analysis - other surveys that clarify metrics and approaches related to the interestingness of geometric theorems. In the conclusion of this article we will introduce the structure of two of these surveys - the second result of this article - and we will discuss some future work.

Firstly, the various strategies used to achieve personalization As robots are expected to become increasingly integrated into are briefly described. Secondly, the effects of personalization people's daily lives, it seems important to create more natural and known to date are discussed. They are presented along with the personalized interactions between humans and robots. Indeed, they personalized parameters, personalized features, used technology, should become companions that provide both mental and physical and use case they relate to. It is observed that various positive effects support. This type of interactions require an emotional intelligence have been discussed in the literature while possible negative from the robot side with a capacity to adapt to the user's state effects seem to require further investigation.