arXiv: Learning
Papers
26503
Papers 10000
1 page of 1,000 pages (10k results)
Newest
#1Jay Whang (University of Texas at Austin)H-Index: 5
#2Qi Lei (Princeton University)H-Index: 15
Last. Alexandros G. Dimakis (University of Texas at Austin)H-Index: 57
view all 0 authors...
We study image inverse problems with a normalizing flow prior. Our formulation views the solution as the maximum a posteriori estimate of the image conditioned on the measurements. This formulation allows us to use noise models with arbitrary dependencies as well as non-linear forward operators. We empirically validate the efficacy of our method on various inverse problems, including compressed sensing with quantized measurements and denoising with highly structured noise patterns. We also prese...
#2Joshua R. LoftusH-Index: 13
Last. Julia StoyanovichH-Index: 17
view all 0 authors...
A significant body of research in the data sciences considers unfair discrimination against social categories such as race or gender that could occur or be amplified as a result of algorithmic decisions. Simultaneously, real-world disparities continue to exist, even before algorithmic decisions are made. In this work, we draw on insights from the social sciences and humanistic studies brought into the realm of causal modeling and constrained optimization, and develop a novel algorithmic framewor...
#2Tommaso CesariH-Index: 2
Last. Vianney PerchetH-Index: 16
view all 0 authors...
We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our setting is motivated by the use case of companies that regularly receive proposals for technological innovations and want to quickly decide whether they are worth implementing. We design an algorithm for learning ROI-maximizing decision-making policies over a sequence of innovation proposals. Our algorithm provably converges to an optimal policy in class \Piat a rate of orde...
#1Nicklas HansenH-Index: 2
Last. Xiaolong WangH-Index: 86
view all 0 authors...
While agents trained by Reinforcement Learning (RL) can solve increasingly challenging tasks directly from visual observations, generalizing learned skills to novel environments remains very challenging. Extensive use of data augmentation is a promising technique for improving generalization in RL, but it is often found to decrease sample efficiency and can even lead to divergence. In this paper, we investigate causes of instability when using data augmentation in common off-policy RL algorithms...
#1Etai LittwinH-Index: 6
Last. Greg YangH-Index: 16
view all 0 authors...
We analyze the learning dynamics of infinitely wide neural networks with a finite sized bottle-neck. Unlike the neural tangent kernel limit, a bottleneck in an otherwise infinite width network al-lows data dependent feature learning in its bottle-neck representation. We empirically show that a single bottleneck in infinite networks dramatically accelerates training when compared to purely in-finite networks, with an improved overall performance. We discuss the acceleration phenomena by drawing s...
#1Shuaicheng Niu (SCUT: South China University of Technology)H-Index: 4
#2Jiaxiang Wu (Tencent)H-Index: 14
Last. Mingkui Tan (SCUT: South China University of Technology)H-Index: 33
view all 0 authors...
In real-world applications, data often come in a growing manner, where the data volume and the number of classes may increase dynamically. This will bring a critical challenge for learning: given the increasing data volume or the number of classes, one has to instantaneously adjust the neural model capacity to obtain promising performance. Existing methods either ignore the growing nature of data or seek to independently search an optimal architecture for a given dataset, and thus are incapable ...
#1Gaurab Bhattacharya (IIT BBS: Indian Institute of Technology Bhubaneswar)
In recent times, the trend in very large scale integration (VLSI) industry is multi-dimensional, for example, reduction of energy consumption, occupancy of less space, precise result, less power dissipation, faster response. To meet these needs, the hardware architecture should be reliable and robust to these problems. Recently, neural network and deep learning has been started to impact the present research paradigm significantly which consists of parameters in the order of millions, nonlinear ...
#1Zhen Huang (USTC: University of Science and Technology of China)
#2Xu Shen (Alibaba Group)H-Index: 9
Last. Xian-Sheng Hua (Alibaba Group)H-Index: 37
view all 0 authors...
Knowledge Distillation (KD) is a popular technique to transfer knowledge from a teacher model or ensemble to a student model. Its success is generally attributed to the privileged information on similarities/consistency between the class distributions or intermediate feature representations of the teacher model and the student model. However, directly pushing the student model to mimic the probabilities/features of the teacher model to a large extent limits the student model in learning undiscov...
#1Rui Yang (THU: Tsinghua University)
#2Meng Fang (TU/e: Eindhoven University of Technology)
Last. Xiu Li (THU: Tsinghua University)H-Index: 17
view all 0 authors...
Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these methods are still limited in efficiency and cannot make full use of experiences. In this paper, we propose Model-based Hindsight Experience Replay (MHER), which exploits experiences more efficiently by leveraging environmental dynamics to generate virtual achi...
#1Shuai Zheng (Beijing Jiaotong University)H-Index: 4
#2Zhenfeng Zhu (Beijing Jiaotong University)H-Index: 14
Last. Yao Zhao (Beijing Jiaotong University)H-Index: 54
view all 0 authors...
Benefiting from the powerful expressive capability of graphs, graph-based approaches have achieved impressive performance in various biomedical applications. Most existing methods tend to define the adjacency matrix among samples manually based on meta-features, and then obtain the node embeddings for downstream tasks by Graph Representation Learning (GRL). However, it is not easy for these approaches to generalize to unseen samples. Meanwhile, the complex correlation between modalities is also ...
12345678910
Top fields of study
Deep learning
Algorithm
Machine learning
Mathematical optimization
Mathematics
Computer science
Artificial neural network
Reinforcement learning