Výsledky vyhledávání - "Suri, Sahaana"

Report

Simple Embodied Language Learning as a Byproduct of Meta-Reinforcement Learning

Autor: Liu, Evan Zheran, Suri, Sahaana, Mu, Tong, Zhou, Allan, Finn, Chelsea

Whereas machine learning models typically learn language by directly training on language tasks (e.g., next-word prediction), language emerges in human children as a byproduct of solving non-language tasks (e.g., acquiring food). Motivated by this ob

Externí odkaz: http://arxiv.org/abs/2306.08400

Zobrazit plný text záznamu

Report

Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins

Autor: Suri, Sahaana, Ilyas, Ihab F., Ré, Christopher, Rekatsinas, Theodoros

Structured data, or data that adheres to a pre-defined schema, can suffer from fragmented context: information describing a single entity can be scattered across multiple datasets or tables tailored for specific business needs, with no explicit linki

Externí odkaz: http://arxiv.org/abs/2106.01501

Zobrazit plný text záznamu

Report

Leveraging Organizational Resources to Adapt Models to New Data Modalities

Autor: Suri, Sahaana, Chanda, Raghuveer, Bulut, Neslihan, Narayana, Pradyumna, Zeng, Yemao, Bailis, Peter, Basu, Sugato, Narlikar, Girija, Re, Christopher, Sethi, Abishek

Publikováno v: PVLDB,13(12): 3396-3410, 2020

As applications in large organizations evolve, the machine learning (ML) models that power them must adapt the same predictive tasks to newly arising data modalities (e.g., a new video content launch in a social media application requires existing te

Externí odkaz: http://arxiv.org/abs/2008.09983

Zobrazit plný text záznamu

Report

CrossTrainer: Practical Domain Adaptation with Loss Reweighting

Autor: Chen, Justin, Gan, Edward, Rong, Kexin, Suri, Sahaana, Bailis, Peter

Domain adaptation provides a powerful set of model training techniques given domain-specific training data and supplemental data with unknown relevance. The techniques are useful when users need to develop models with data from varying sources, of va

Externí odkaz: http://arxiv.org/abs/1905.02304

Zobrazit plný text záznamu

Report

DROP: Dimensionality Reduction Optimization for Time Series

Autor: Suri, Sahaana, Bailis, Peter

Publikováno v: DEEM'19: Proceedings of the 3rd International Workshop on Data Management for End-to-End Machine Learning (2019)

Dimensionality reduction is a critical step in scaling machine learning pipelines. Principal component analysis (PCA) is a standard tool for dimensionality reduction, but performing PCA over a full dataset can be prohibitively expensive. As a result,

Externí odkaz: http://arxiv.org/abs/1708.00183

Zobrazit plný text záznamu

Report

Real-time Cooperative Communication for Automation over Wireless

Autor: Swamy, Vasuki Narasimha, Suri, Sahaana, Rigge, Paul, Weiner, Matthew, Ranade, Gireeja, Sahai, Anant, Nikolic, Borivoje

High-performance industrial automation systems rely on tens of simultaneously active sensors and actuators and have stringent communication latency and reliability requirements. Current wireless technologies like WiFi, Bluetooth, and LTE are unable t

Externí odkaz: http://arxiv.org/abs/1609.02968

Zobrazit plný text záznamu

Report

MacroBase: Prioritizing Attention in Fast Data

Autor: Bailis, Peter, Gan, Edward, Madden, Samuel, Narayanan, Deepak, Rong, Kexin, Suri, Sahaana

As data volumes continue to rise, manual inspection is becoming increasingly untenable. In response, we present MacroBase, a data analytics engine that prioritizes end-user attention in high-volume fast data streams. MacroBase enables efficient, accu

Externí odkaz: http://arxiv.org/abs/1603.00567

Zobrazit plný text záznamu