10.04.18 34:48 Recharging Bandits
We introduce a general model of bandit problems in which the expected payout of an arm is an increasing concave function of the time since it was last played.
1 527
56.2
10.04.18 39:29 Measuring Sample Quality with Stein's Method
To improve the efficiency of Monte Carlo estimation, practitioners are turning to biased Markov chain Monte Carlo procedures that trade-off asymptotic exactness for computational speed.
4 094
27.5
10.04.18 27:58 Approximating General Norms by Euclidean Beyond the John's Ellipsoid
John's theorem proved in 1948 states that any centrally-symmetric convex body in R^d can be sandwiched by two ellipsoids up to a factor of sqrt{d}.
2 164
44.7
10.04.18 1:02:12 Observing and Controlling Distributed Systems with Cross-Cutting Tools
Distributed systems represent some of the most interesting and successful computing applications in use today, from modern web applications and social networks, to data analytics and large-scale
1 216
67.2
10.04.18 1:23:51 Inherent Trade-Offs in Algorithmic Fairness
Recent discussion in the public sphere about classification by algorithms has involved tension between competing notions of what it means for such a classification to be fair to different groups.
6 319
26.3
10.04.18 33:45 AI for the Developing World with Dr. Ranveer Chandra
Episode 18 | April 4, 2018 When we think about artificial intelligence and the “world of the future,” our vision is usually more Jetsons than Green Acres. But for Dr.
1 788
29.5
09.04.18 2:30 Project Zanzibar: A Portable and Flexible Tangible Interaction Platform
Project Zanzibar, a completely new sensing platform in the form of a flexible, portable mat that has the ability to locate, sense and communicate with objects as well as sense a user’s touch.
90 774
56.9
05.04.18 1:26:56 Anomaly Detection: Algorithms, Explanations, Applications
Anomaly detection is important for data cleaning, cybersecurity, and robust AI systems.
95 780
25.7
04.04.18 1:29:02 Unsupervised Streaming Cyber-Analytics
The supervised learning approach to cyber-analytics has proven rather successful.
1 644
41.8
04.04.18 1:23:15 Neural Representations for Program Analysis and Synthesis
Representing a program as a numerical vector (i.e., neural representation) enables handling discrete programs using continuous optimization approaches, and thus opens up new opportunities to tackle
1 786
42.1
04.04.18 1:28:59 The Gift of Failure: Fostering Intrinsic Motivation and Resilience in Kids
Veteran teacher, author, and education journalist Jessica Lahey breaks down the research on motivation, resilience and learning, and explains how autonomy-supportive parenting and teaching not only
8 988
25.7
02.04.18 1:09:17 NeuroSAT: Learning a SAT Solver from Single-Bit Supervision
I will present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability.
9 718
13.7
02.04.18 51:45 Using Efficient Oblivious Computation to Keep Data Private and Obfuscate Programs
Protecting sensitive user data and proprietary programs are fundamental and important challenges.
1 435
59.4
02.04.18 1:08:14 Neural Models for Information Retrieval
In the last few years, neural representation learning approaches have achieved very good performance on many natural language processing (NLP) tasks, such as language modeling and machine translation.
22 960
14.8
02.04.18 2:13 DL Workspace: Running TensorFlow
The tutorial video is part of DL Workspace series, which describes an open source toolkit for turn-key AI Cluster setup and operation.
1 074
89.2
02.04.18 1:05:09 Designing Gaze Visualizations for Remote Collaboration and Learning
Technological advances are improving our ability to work and learn together, even when separated by distance.
1 687
23.1
29.03.18 33:19 When Psychology Meets Technology with Dr. Daniel McDuff
Episode 17 | March 28, 2018 Dr.
5 673
14.4
24.03.18 1:01:34 Monopoly Without a Monopolist: An Economic Analysis of Bitcoin
Owned by nobody and controlled by an almost immutable protocol, the Bitcoin payment system is a platform with two main constituencies: users and profit-seeking miners who maintain the system's
2 067
29.6
24.03.18 56:43 Enabling Low-power Computation, Sensing, and Communication on Internet-of-Things
In recent years, we have seen a massive number of IoT devices shipped to the market. The vision is that we are going to embrace a world where IoT devices are ubiquitously deployed.
1 446
36.7
23.03.18 1:02:26 Further Adventures in Evidence-Based Security
Over the last decade, our group has undertaken an "evidence-based" approach to measure, analyze, and undermine various kinds of abuse and cybercrime on the Internet.
1 321
73.1
23.03.18 1:10:44 Recent Results on Learning Filters and Style Transfer
In the first part of this talk, I will present recent results on learning image filters for low-level vision.
1 643
38.8
23.03.18 1:02:17 Closing the Loop on Secure System Design
Despite decades of research building secure operating systems, many deployed systems must still choose between flexible application APIs and security.
1 516
55.8
23.03.18 53:04 Exploiting Structure Information in Machine Learning
Machine learning has recently witnessed revolutionary success in a wide spectrum of domains.
1 610
27.9
23.03.18 31:15 Natural Language Processing: State-of-Art: Observations and Insights
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
4 257
32.7
22.03.18 24:08 State of Computer Vision
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
3 229
24.7
22.03.18 29:15 Academic Research Summit 2018 - Welcome & Introductory Session
The Academic Research Summit, co-organized by Microsoft Research and the Association for Computing Machinery, is a forum to foster meaningful discussion among the Indian computer science research
1 199
44.1
22.03.18 24:09 Generalization Error Bounds for Extreme Multi-class Classification
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
2 719
30.9
22.03.18 10:25 A Reduction Principle for Generalizing Bona Fide Risk Bounds in Multi-class Setting
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
1 110
36.7
22.03.18 9:24 Precision-Recall versus Accuracy and the Role of Large Data Sets
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
2 343
33.6
22.03.18 16:19 Active Positive Semidefinite Matrix Completion With Applications to Large Scale Bandit Problems
Extreme classification is a rapidly growing research area focusing on multi-class and multi-label problems involving an extremely large number of labels.
1 420
58.8