-
公开(公告)号：US20250028751A1
公开(公告)日：2025-01-23
申请号：US18355901
申请日：2023-07-20
Applicant: Adobe Inc.
Inventor： Tong Yu , Kaige Xie , Haoliang Wang , Junda Wu , Handong Zhao , Ruiyi Zhang , Kanak Vivek Mahadik , Ani Nenkova
Abstract: Dialogue skeleton assisted prompt transfer for dialogue summarization techniques are described that support training of a language model to perform dialogue summarization in a few-shot scenario. A processing device, for instance, receives a training dataset that includes training dialogues. The processing device then generates dialogue skeletons based on the training dialogues using one or more perturbation-based probes. The processing device trains a language model using prompt transfer between a source task, e.g., dialogue state tracking, and a target task, e.g., dialogue summarization, using the dialogue skeletons as supervision. The processing device then receives an input dialogue and uses the trained language model to generate a summary of the input dialogue.
-
公开(公告)号：US20220374276A1
公开(公告)日：2022-11-24
申请号：US17324692
申请日：2021-05-19
Applicant: Adobe Inc.
Inventor： Subrata Mitra , Sunav Choudhary , Sheng Yang , Kanak Vivek Mahadik , Samir Khuller
Abstract: Techniques are provided for scheduling multiple jobs on one or more cloud computing instances, which provide the ability to select a job for execution from among a plurality of jobs, and to further select a designated instance from among a plurality of cloud computing instances for executing the selected job. The job and the designated instance are each selected based on a probability distribution that a cost of executing the job on the designated instance does not exceed the budget. The probability distribution is based on several factors including a cost of prior executions of other jobs on the designated instance and a utility function that represents a value associated with a progress of each job. By scheduling select jobs on discounted cloud computing instances, the aggregate utility of the jobs can be maximized or otherwise improved for a given budget.
-
公开(公告)号：US12164965B2
公开(公告)日：2024-12-10
申请号：US17443928
申请日：2021-07-28
Applicant: ADOBE INC.
Inventor： Kanak Vivek Mahadik
IPC: G06F9/50
Abstract: Systems and methods that enable the efficient and adaptive allocation of resources dedicated to a container-based computation (e.g., one or more information processing tasks) are provided. A container controller is employed to launch and dynamically update (e.g., manage) the resource allocation (e.g., indicated by a selected configuration) for a set of containers. The container controller implements a Markov Decision Process (MDP)-based control loop to adaptively configure (e.g., allocate resources for) and reconfigure the set of containers. In some embodiments, the MDP of the control loop is a single-state MDP (e.g., a multi-armed bandit decision process). In such embodiments, each possible configuration for the set of containers is an arm on the multi-armed bandit.
-
公开(公告)号：US11915054B2
公开(公告)日：2024-02-27
申请号：US17324692
申请日：2021-05-19
Applicant: Adobe Inc.
Inventor： Subrata Mitra , Sunav Choudhary , Sheng Yang , Kanak Vivek Mahadik , Samir Khuller
CPC classification number: G06F9/5038 , G06F9/4818 , G06F9/4856 , G06F9/4881
Abstract: Techniques are provided for scheduling multiple jobs on one or more cloud computing instances, which provide the ability to select a job for execution from among a plurality of jobs, and to further select a designated instance from among a plurality of cloud computing instances for executing the selected job. The job and the designated instance are each selected based on a probability distribution that a cost of executing the job on the designated instance does not exceed the budget. The probability distribution is based on several factors including a cost of prior executions of other jobs on the designated instance and a utility function that represents a value associated with a progress of each job. By scheduling select jobs on discounted cloud computing instances, the aggregate utility of the jobs can be maximized or otherwise improved for a given budget.
-
Patent Agency Ranking
公开(公告)号：US11487579B2
公开(公告)日：2022-11-01
申请号：US16867104
申请日：2020-05-05
Applicant: ADOBE INC.
Inventor： Kanak Vivek Mahadik , Ryan A. Rossi , Sana Malik Lee , Georgios Theocharous , Handong Zhao , Gang Wu , Youngsuk Park
Abstract: A system and method for automatically adjusting computing resources provisioned for a computer service or application by applying historical resource usage data to a predictive model to generate predictive resource usage. The predictive resource usage is then simulated for various service configurations, determining scaling requirements and resource wastage for each configuration. A cost value is generated based on the scaling requirement and resource wastage, with the cost value for each service configuration used to automatically select a configuration to apply to the service. Alternatively, the method for automatically adjusting computer resources provisioned for a service may include receiving resource usage data of the service, applying it to a linear quadratic regulator (LQR) to find an optimal stationary policy (treating the resource usage data as states and resource-provisioning variables as actions), and providing instructions for configuring the service based on the optimal stationary policy.
-
公开(公告)号：US20250005289A1
公开(公告)日：2025-01-02
申请号：US18343389
申请日：2023-06-28
Applicant: Adobe Inc.
Inventor： Haoliang Wang , Kaige Xie , Tong Yu , Junda Wu , Handong Zhao , Ruiyi Zhang , Kanak Vivek Mahadik , Ani Nenkova
Abstract: Dialogue state aware dialogue summarization techniques are described that enable generation of dialogue summaries from target domains with limited training data. A content processing system, for instance, generates one or more clusters based on training dialogues from one or more source domains. The clusters represent domain-specific features of the training dialogues and are further based on dialogue states of the training dialogues. The content processing system trains a machine learning model to generate summaries of dialogues by using the one or more clusters as prefixes in a prefix-tuning approach. The content processing system receives an input that includes a dialogue from a target domain. The content processing system generates an input prompt based on the dialogue and the one or more clusters, and the model generates a summary of the dialogue based on the input prompt.
-
7.发明公开公开(公告)号：US20230376356A1
公开(公告)日：2023-11-23
申请号：US17749577
申请日：2022-05-20
Applicant: ADOBE INC.
Inventor： Kanak Vivek Mahadik , Tong Yu
CPC classification number: G06F9/5077 , G06F9/5033 , G06F9/5038 , G06K9/6262
Abstract: Systems and methods that enable the efficient and adaptive allocation of resources dedicated to a virtualized resource-based computation (e.g., one or more information processing tasks) are provided. In one embodiment, a reward model is generated based on a set of statistical distributions, for example, in response to receiving a request to launch a set of VCRs. Thereafter, an expected reward is predicting for each configuration of a set of configurations based on the reward model and one or more parameters of the corresponding configuration. The expected reward indicates an efficiency in distribution or allocation of physical computation resources to the set of VCRs. A configuration of the set of configurations is selected based on the predicted expected reward for the configuration. The set of VCRs are then configured with the selected configuration.
-
公开(公告)号：US20220138557A1
公开(公告)日：2022-05-05
申请号：US17089157
申请日：2020-11-04
Applicant: Adobe Inc.
Inventor： Ryan A. Rossi , Hongjie Chen , Kanak Vivek Mahadik , Sungchul Kim
IPC: G06N3/08 , G06N3/04 , G06F16/2458
Abstract: In implementations of deep hybrid graph-based forecasting systems, a computing device implements a forecast system to receive time-series data describing historic computing metric values for a plurality of processing devices. The forecast system determines dependency relationships between processing devices of the plurality of processing devices based on time-series data of the processing devices. Time-series data of each processing device is represented as a node of a graph and the nodes are connected based on the dependency relationships. The forecast system generates an indication of a future computing metric value for a particular processing device by processing a first set of the time-series data using a relational global model and processing a second set of the time-series data using a relational local model. The first and second sets of the time-series data are determined based on a structure of the graph.
-
公开(公告)号：US20210357255A1
公开(公告)日：2021-11-18
申请号：US16867104
申请日：2020-05-05
Applicant: ADOBE INC.
Inventor： Kanak Vivek Mahadik , Ryan A. Rossi , Sana Malik Lee , Georgios Theocharous , Handong Zhao , Gang Wu , Youngsuk Park
Abstract: A system and method for automatically adjusting computing resources provisioned for a computer service or application by applying historical resource usage data to a predictive model to generate predictive resource usage. The predictive resource usage is then simulated for various service configurations, determining scaling requirements and resource wastage for each configuration. A cost value is generated based on the scaling requirement and resource wastage, with the cost value for each service configuration used to automatically select a configuration to apply to the service. Alternatively, the method for automatically adjusting computer resources provisioned for a service may include receiving resource usage data of the service, applying it to a linear quadratic regulator (LQR) to find an optimal stationary policy (treating the resource usage data as states and resource-provisioning variables as actions), and providing instructions for configuring the service based on the optimal stationary policy.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.023 seconds)
