相关论文: Towards Learning Universal Hyperparameter Optimize…

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and…

We present a High-Resolution Transformer (HRFormer) that learns high-resolution representations for dense prediction tasks, in contrast to the original Vision Transformer that produces low-resolution representations and has high memory and…

In recent years, imitation learning has made progress in the field of robotic manipulation. However, it still faces challenges when addressing complex long-horizon tasks with deformable objects, such as high-dimensional state spaces,…

In the paper, we propose a novel methodology to map learning algorithms on data (performance map) in order to gain more insights in the distribution of their performances across their parameter space. This methodology provides useful…

Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous methods for 3D human pose estimation (HPE) have often relied on 2D image features and sequential 2D annotations. Furthermore, the training of these…

Modern machine learning models are often constructed taking into account multiple objectives, e.g., minimizing inference time while also maximizing accuracy. Multi-objective hyperparameter optimization (MHPO) algorithms return such…

Meta-reinforcement learning (Meta-RL) has attracted attention due to its capability to enhance reinforcement learning (RL) algorithms, in terms of data efficiency and generalizability. In this paper, we develop a bilevel optimization…

Training an effective deep learning model to learn ocean processes involves careful choices of various hyperparameters. We leverage the advanced search algorithms for multiobjective optimization in DeepHyper, a scalable hyperparameter…

In robotics, methods and softwares usually require optimizations of hyperparameters in order to be efficient for specific tasks, for instance industrial bin-picking from homogeneous heaps of different objects. We present a developmental…

A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the…

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning -- a key tool for performing meta-learning -- learns a…

We propose UniT, a Unified Transformer model to simultaneously learn the most prominent tasks across different domains, ranging from object detection to natural language understanding and multimodal reasoning. Based on the transformer…

Optimization aims at selecting a feasible set of parameters in an attempt to solve a particular problem, being applied in a wide range of applications, such as operations research, machine learning fine-tuning, and control engineering,…

A typical assumption in supervised machine learning is that the train (source) and test (target) datasets follow completely the same distribution. This assumption is, however, often violated in uncertain real-world applications, which…

Currently, this paper is under review in IEEE. Transformers have intrigued the vision research community with their state-of-the-art performance in natural language processing. With their superior performance, transformers have found their…

Control tuning and adaptation present a significant challenge to the usage of robots in diverse environments. It is often nontrivial to find a single set of control parameters by hand that work well across the broad array of environments…

Algorithm design is a laborious process and often requires many iterations of ideation and validation. In this paper, we explore automating algorithm design and present a method to learn an optimization algorithm, which we believe to be the…

We propose a supervised learning algorithm for machine learning applications. Contrary to the model developing in the classical methods, which treat training, validation, and test as separate steps, in the presented approach, there is a…

Time series forecasting underpins vital decision-making across various sectors, yet raw predictions from sophisticated models often harbor systematic errors and biases. We examine the Forecast-Then-Optimize (FTO) framework, pioneering its…

The performance of policy gradient methods is sensitive to hyperparameter settings that must be tuned for any new application. Widely used grid search methods for tuning hyperparameters are sample inefficient and computationally expensive.…