More Like this

1. Robustness of Conditional GANs to Noisy Labels

   Thekumparampil, Kiran Koshy ; Khetan, Ashish ; Lin, Zinan ; Oh, Sewoong ( December 2018 , Advances in neural information processing systems)

   We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator to produce samples with clean labels. This approach of passing through a matching noisy channel is justified by corresponding multiplicative approximation bounds between the loss of the RCGAN and the distance between the clean real distribution and the generator distribution. This shows that the proposed approach is robust, when used with a carefully chosen discriminator architecture, known as projection discriminator. When the distribution of the noise is not known, we provide an extension of our architecture, which we call RCGAN-U, that learns the noise model simultaneously while training the generator. We show experimentally on MNIST and CIFAR-10 datasets that both the approaches consistently improve upon baseline approaches, and RCGAN-U closely matches the performance of RCGAN. 

   more » « less
2. Robustness of conditional GANs to noisy labels

   Thekumparampil, Kiran Koshy ; Khetan, Ashish ; Lin, Zinan ; Oh, Sewoong ( December 2018 , Advances in neural information processing systems)

   We study the problem of learning conditional generators from noisy labeled samples, where the labels are corrupted by random noise. A standard training of conditional GANs will not only produce samples with wrong labels, but also generate poor quality samples. We consider two scenarios, depending on whether the noise model is known or not. When the distribution of the noise is known, we introduce a novel architecture which we call Robust Conditional GAN (RCGAN). The main idea is to corrupt the label of the generated sample before feeding to the adversarial discriminator, forcing the generator to produce samples with clean labels. This approach of passing through a matching noisy channel is justified by accompanying multiplicative approximation bounds between the loss of the RCGAN and the distance between the clean real distribution and the generator distribution. This shows that the proposed approach is robust, when used with a carefully chosen discriminator architecture, known as projection discriminator. When the distribution of the noise is not known, we provide an extension of our architecture, which we call RCGAN-U, that learns the noise model simultaneously while training the generator. We show experimentally on MNIST and CIFAR-10 datasets that both the approaches consistently improve upon baseline approaches, and RCGAN-U closely matches the performance of RCGAN. 

   more » « less
3. Rethinking Sampling in 3D Point Cloud Generative Adversarial Networks

   Wang, He ; Jiang, Zetian ; Yi, Li ; Mo, Kaichun ; Su, Hao ; Guibas, Leonidas ( January 2021 , Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshop)

   null (Ed.)

   In this paper, we examine the long-neglected yet important effects of point sampling patterns in point cloud GANs. Through extensive experiments, we show that sampling-insensitive discriminators (e.g.PointNet-Max) produce shape point clouds with point clustering artifacts while sampling-oversensitive discriminators (e.g. PointNet++, DGCNN) fail to guide valid shape generation. We propose the concept of sampling spectrum to depict the different sampling sensitivities of discriminators. We further study how different evaluation metrics weigh the sampling pattern against the geometry and propose several perceptual metrics forming a sampling spectrum of metrics. Guided by the proposed sampling spectrum, we discover a middle-point sampling-aware baseline discriminator, PointNet-Mix, which improves all existing point cloud generators by a large margin on sampling-related metrics. We point out that, though recent research has been focused on the generator design, the main bottleneck of point cloud GAN actually lies in the discriminator design. Our work provides both suggestions and tools for building future discriminators. We will release the code to facilitate future research. 

   more » « less
4. Bilateral Contracts Between NGPPs and Renewable Plants Can Increase Penetration of Renewables

   https://doi.org/10.23919/ACC.2018.8431253  

   Aguiar, Nayara ; Gupta, Vijay ; Khargonekar, Pramod P. ; Chakraborty, Indraneel ( June 2018 , 2018 Annual American Control Conference (ACC))

   As the renewable penetration in the grid increases, the grid-takes-all-renewable paradigm will no longer be sustainable. We consider a day-ahead (DA) electricity market composed of a renewable generator, a natural gas power plant (NGPP) and a coal power plant (CPP). Each player provides the Independent System Operator (ISO) with their commitment and their asking price. The ISO schedules the generators using a least-cost strategy. Because of the intrinsic uncertainty of the renewable generation, the renewable player might be unable to meet its DA commitment. In the event of a shortfall, the renewable generator incurs a penalty so that the non-renewable sources are not forced to consume the cost of renewable intermittence. It has been recognized that such a penalty can lead to conservative bidding by the renewable generator, which may lead to lower than desired penetration of renewable energy in the grid. We formulate and analyze a contract between the renewable producer and the NGPP so that the NGPP reserves some amount of natural gas to hedge the renewable producer against shortfalls. Expressions for the optimal commitments of the players and for the optimal reserve contract are derived. When a reserve contract is established, we observe an increase both in the average profit of the players involved and in the renewable participation in the market. Thus, we show that a Pareto-optimal contract between market players can improve renewable penetration. 

   more » « less
5. Equilibrium analysis of electricity markets with day-ahead market power mitigation and real-time intercept bidding

   https://doi.org/10.1145/3538637.3538839  

   Bansal, Rajni Kant ; Chen, Yue ; You, Pengcheng ; Mallada, Enrique ( June 2022 , Proceedings of the Thirteenth ACM International Conference on Future Energy Systems (e-Energy))

   Electricity markets are cleared by a two-stage, sequential process consisting of a forward (day-ahead) market and a spot (real-time) market. While their design goal is to achieve efficiency, the lack of sufficient competition introduces many opportunities for price manipulation. To discourage this phenomenon, some Independent System Operators (ISOs) mandate generators to submit (approximately) truthful bids in the day-ahead market. However, without fully accounting for all participants' incentives (generators and loads), the application of such a mandate may lead to unintended consequences. In this paper, we model and study the interactions of generators and inelastic loads in a two-stage settlement where generators are required to bid truthfully in the day-ahead market. We show that such mandate, when accounting for generator and load incentives, leads to a {generalized} Stackelberg-Nash game where load decisions (leaders) are performed in day-ahead market and generator decisions (followers) are relegated to the real-time market. Furthermore, the use of conventional supply function bidding for generators in real-time, does not guarantee the existence of a Nash equilibrium. This motivates the use of intercept bidding, as an alternative bidding mechanism for generators in the real-time market. An equilibrium analysis in this setting, leads to a closed-form solution that unveils several insights. Particularly, it shows that, unlike standard two-stage markets, loads are the winners of the competition in the sense that their aggregate payments are less than that of the competitive equilibrium. Moreover, heterogeneity in generators cost has the unintended effect of mitigating loads market power. Numerical studies validate and further illustrate these insights. 

   more » « less