Related papers: A Memetic Walrus Algorithm with Expert-guided Stra…

Classification accuracy provided by a machine learning model depends a lot on the feature set used in the learning process. Feature Selection (FS) is an important and challenging pre-processing technique which helps to identify only the…

We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to new instantiations of themselves recursively. Recursive agents implement an…

Training large language models requires jointly configuring two interdependent aspects of the system: the global batch size, which governs statistical efficiency, and the 3D parallelism strategy, which governs hardware throughput. Existing…

This paper aims to predict optimal solutions for combinatorial optimization problems (COPs) via machine learning (ML). To find high-quality solutions efficiently, existing work uses a ML prediction of the optimal solution to guide heuristic…

Privacy is important when dealing with sensitive personal information in machine learning models, which require large data sets for training. In the energy field, access to household prosumer energy data is crucial for energy predictions to…

Automatic prompt optimization (APO) hinges on the quality of its evaluation signal, yet scoring every prompt candidate on the full training set is prohibitively expensive. Existing methods either fix a single evaluation subset before…

Optimization algorithms are core methods by which machine learning models iteratively minimize loss functions, update parameters, learn from data, and improve performance. Momentum SGD and AdamW represent two important optimization…

Many machine learning problems involve iteratively and alternately optimizing different task objectives with respect to different sets of parameters. Appropriately scheduling the optimization of a task objective or a set of parameters is…

To avoid myopic behavior, multi-step lookahead Bayesian optimization (BO) algorithms consider the sequential nature of BO and have demonstrated promising results in recent years. However, owing to the curse of dimensionality, most of these…

Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is…

Reward-based alignment methods for large language models (LLMs) face two key limitations: vulnerability to reward hacking, where models exploit flaws in the reward signal; and reliance on brittle, labor-intensive prompt engineering when…

Optimal resource allocation in modern communication networks calls for the optimization of objective functions that are only accessible via costly separate evaluations for each candidate solution. The conventional approach carries out the…

In this thesis, we focus on the design of an automatic algorithms that provide personalized ranking by adapting to the current conditions. To demonstrate the empirical efficiency of the proposed approaches we investigate their applications…

Recently, multi-objective optimization (MOO) has gained attention for its broad applications in ML, operations research, and engineering. However, MOO algorithm design remains in its infancy and many existing MOO methods suffer from…

With the rapid emergence of K-12 online learning platforms, a new era of education has been opened up. It is crucial to have a dropout warning framework to preemptively identify K-12 students who are at risk of dropping out of the online…

Multi-agent systems (MAS) are foundational in simulating complex real-world scenarios involving autonomous, interacting entities. However, traditional MAS architectures often suffer from rigid coordination mechanisms and difficulty adapting…

The implementation of teaching interventions in learning needs has received considerable attention, as the provision of the same educational conditions to all students, is pedagogically ineffective. In contrast, more effectively considered…

Multiple sequences alignment (MSA) is a traditional and challenging task for time-series analyses. The MSA problem is formulated as a discrete optimization problem and is typically solved by dynamic programming. However, the computational…

Continual Learning addresses the challenge of learning a number of different tasks sequentially. The goal of maintaining knowledge of earlier tasks without re-accessing them starkly conflicts with standard SGD training for artificial neural…

Bayesian optimization (BO) is a popular method to optimize costly black-box functions. While traditional BO optimizes each new target task from scratch, meta-learning has emerged as a way to leverage knowledge from related tasks to optimize…