Related papers: Why Warmup the Learning Rate? Underlying Mechanism…

Model Predictive Control lacks the ability to escape local minima in nonconvex problems. Furthermore, in fast-changing, uncertain environments, the conventional warmstart, using the optimal trajectory from the last timestep, often falls…

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Deep learning-based Natural Language Processing (NLP) models are vulnerable to adversarial attacks, where small perturbations can cause a model to misclassify. Adversarial Training (AT) is often used to increase model robustness. However,…

Machine learning models are not static and may need to be retrained on slightly changed datasets, for instance, with the addition or deletion of a set of data points. This has many applications, including privacy, robustness, bias…

The success of modern deep learning is attributed to two key elements: huge amounts of training data and large model sizes. Where a vast amount of data allows the model to learn more features, the large model architecture boosts the…

Deep reinforcement learning has been successful in a variety of tasks, such as game playing and robotic manipulation. However, attempting to learn \textit{tabula rasa} disregards the logical structure of many domains as well as the wealth…

In this overview article we will consider the deliberate restarting of algorithms, a meta technique, in order to improve the algorithm's performance, e.g., convergence rates or approximation guarantees. One of the major advantages is that…

Recently, Large Language Models (LLMs) have demonstrated outstanding performance across a wide range of downstream language tasks. Temperature sampling is a commonly used decoding strategy for LLMs' generation process. However, a fixed…

Recent works have demonstrated great success in pre-training large-scale autoregressive language models on massive GPUs. To reduce the wall-clock training time, a common practice is to increase the batch size and learning rate. However,…

Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy. However, their increasing energy consumption has raised concerns about their…

Recently, embedding techniques have achieved impressive success in recommender systems. However, the embedding techniques are data demanding and suffer from the cold-start problem. Especially, for the cold-start item which only has limited…

In modern industrial systems, diagnosing faults in time and using the best methods becomes more and more crucial. It is possible to fail a system or to waste resources if faults are not detected or are detected late. Machine learning and…

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Adversarial Training (AT) with Projected Gradient Descent (PGD) is an effective approach for improving the robustness of the deep neural networks. However, PGD AT has been shown to suffer from two main limitations: i) high computational…

Class-incremental learning of deep networks sequentially increases the number of classes to be classified. During training, the network has only access to data of one task at a time, where each task contains several classes. In this…

Training deep neural networks is a highly nontrivial task, involving carefully selecting appropriate training algorithms, scheduling step sizes and tuning other hyperparameters. Trying different combinations can be quite labor-intensive and…

Recent advancements in large language models (LLMs) have demonstrated impressive chain-of-thought reasoning capabilities, with reinforcement learning (RL) playing a crucial role in this progress. While "aha moment" patterns--where models…

Recent advances on deep learning models come at the price of formidable training cost. The increasing model size is one of the root causes, but another less-emphasized fact is that data scale is actually increasing at a similar speed as…

Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fraction of the training data. A major roadblock faced when…

Trajectory optimization is a cornerstone of modern robot autonomy, enabling systems to compute trajectories and controls in real-time while respecting safety and physical constraints. However, it has seen limited usage in spaceflight…