Upcoming Events

Maximal Mutual Information Predictive Coding for Natural Language Processing

Duke Computer Science Colloquium
Speaker Name
Karl Stratos
Location
LSRC D106
Date and Time
-

Neural predictive coding is an enormously successful approach to unsupervised representation learning in natural language processing. In this approach, a large-scale neural language model is trained to predict the missing signal (e.g., next word, next sentence) and the trained model is used in downstream tasks to produce useful text representations. While effective, it is computationally difficult to work with and yields uninterpretable representations.

Architecting Transactional Key-Value Storage Systems with Precision Time and Software-de ned Storage

Ph. D. Defense
Speaker Name
Pulkit Misra
Location
LSRC D344
Date and Time
-

Transactional key-value storage is an important service offered by cloud service providers for building applications (e.g., Amazon DynamoDB, Microsoft CosmosDB, Google Spanner). This type of service is popular because it provides high-level guarantees like consistency, scalability and fault-tolerance to ease application development and deployment on the cloud.

Transition Space Distance Learning

Master's Defense
Speaker Name
Mark Nemecek
Location
LSRC D106
Date and Time
-

The notion of distance plays and important role in many reinforcement learning (RL) techniques. This role may be explicit, as in some non-parametric approaches, or it may be implicit in the architecture of the feature space. The ability to learn distance functions tailored for RL tasks could, thus, benefit many different RL paradigms.

Transaction Processing at Scale

Duke Computer Science Colloquium
Speaker Name
Xiangyao Yu
Location
LSRC D106
Date and Time
-

Online transaction processing (OLTP) is critical for applications including finance, e-commerce, social networks, and healthcare. The increasing performance demands of these applications require OLTP to scale massively. Concurrency control is a major scalability bottleneck in such systems. 

Towards Generalization and Efficiency in Reinforcement Learning

Duke Computer Science Colloquium
Speaker Name
Wen Sun
Location
LSRC D106
Date and Time
-

In classic supervised machine learning, a learning agent behaves as a passive observer: it receives examples from some external environment which it has no control over and then makes predictions. Reinforcement Learning (RL), on the other hand, is fundamentally interactive : an autonomous agent must learn how to behave in an unknown and possibly hostile environment, by actively interacting with the environment to collect useful feedback.

Enabling Fine-Grained Permissions in Smartphones

Ph. D. Defense
Speaker Name
Nisarg Raval
Location
LSRC D344
Date and Time
-

The increasing popularity of smart devices that continuously monitor various aspects of users' life and the prevalence of third-party services that utilize these data feeds have resulted in a serious threat to users' privacy. One-sided focus on the utility of these applications (apps) and lack of proper access control mechanism often lead to inadvertent (or deliberate) leak of sensitive information about users. At the core of protecting user data on smart devices lies the permissions framework. It arbitrates apps' accesses to resources on the device.

Formulas versus Circuits

Duke Computer Science/Mathematics Colloquium
Speaker Name
Ben Rossman
Location
LSRC D106
Date and Time
-

Boolean circuits (acyclic networks of AND, OR, NOT gates) are a simple abstract model of computer hardware. Boolean formulas (circuits with the structure of a tree) are an even simpler “memoryless” model, in which the result of each subcomputation is used only once. Despite this apparent limitation, it is unknown whether formulas are strictly less powerful than circuits of comparable size. This fundamental question of formulas vs circuits (formally whether NC1 equals P/poly) is one of the biggest open problems in complexity theory.

Detecting and Reducing Resource Interferences in Data Analytics Frameworks

Ph. D. Defense
Speaker Name
Prajakta Kalmegh
Location
LSRC D344
Date and Time
-

Data analytics frameworks on shared clusters host a large number of diverse workloads submitted by multiple tenants. Modern cluster schedulers incentivize users to share the cluster resources by promising fairness and isolation along with high performance and resource utilization. Nevertheless, it is hard to meet these guarantees as resource contentions among such collocated workloads cause significant performance issues and is one of the key reasons for unpredictable performance and missed workload Service-Level-Agreements (SLAs) in data analytics frameworks.

Rethinking the Hardware-Software Contract: Enabling Practical and General Cross-Layer Optimizations

Duke Computer Science Colloquium
Speaker Name
Nandita Vijaykumar
Location
LSRC D106
Date and Time
-

Layered abstractions in the computing stack are critical to building complex systems, but the existing *interfaces* between layers restrict what can be done at each level. Enhancing cross-layer interfaces--specifically, the hardware-software interface--is crucial towards addressing two important and hard-to-solve challenges in computer systems today: First, significant effort and expertise are required to write high-performance code that harnesses the full potential of today’s diverse and sophisticated hardware.

Automating Memory Management in Data Analytics

Ph. D. Defense
Speaker Name
Mayuresh Kunjir
Location
LSRC D344
Date and Time
-

Recent years have seen unprecedented growth in the volume, velocity, and variety of the data managed by data analytics platforms. At the same time, the skilled IT staff required to develop and operate the datacenters are going up at a much smaller pace. This trend suggests a big interest in making the data analytics platforms more autonomic/self-driving. There are, however, several major challenges in this task.

Visual Question Answering and Beyond

Duke Computer Science Colloquium
Speaker Name
Aishwarya Agrawal
Location
LSRC D106
Date and Time
-

In this talk, I will present our work on a multi-modal AI task called Visual Question Answering (VQA) -- given an image and a natural language question about the image (e.g., “What kind of store is this?”, “Is it safe to cross the street?”), the machine’s task is to automatically produce an accurate natural language answer (“bakery”, “yes”).

Hardware Acceleration in the World of Emerging Applications

Duke Computer Science/Electrical Computer Engineering Colloquium
Speaker Name
Lisa Wu
Location
LSRC D106
Date and Time
-

Semiconductor technology scaling coming to a screeching halt coupled with the explosion of data in almost every facet of our lives makes processing large volumes of data efficiently a critical problem to solve. In this talk, I will highlight three main challenges in designing accelerators and demonstrate that domain-specific hardware acceleration and specialization can provide orders of magnitude in compute efficiency for emerging applications.

Discrete Optimization Meets Machine Learning

Duke Computer Science Colloquium
Speaker Name
Elias Khalil
Location
LSRC D106
Date and Time
-

Discrete Optimization algorithms underlie intelligent decision-making in a wide variety of domains. From airline fleet scheduling to kidney exchanges and data center resource management, decisions are often modeled with binary on/off variables that are subject to operational and financial constraints.

Providing Secure Internet Services with Insecure Infrastructure

Duke Computer Science/Electrical Computer Engineering Colloquium
Speaker Name
Yixin Sun
Location
Fitzpatrick Center Schiciano Auditorium Side B
Date and Time
-

The insecurity of Internet services can lead to disastrous consequences – confidential communications can be monitored, financial information can be stolen, and our critical Internet infrastructure can be crippled. However, many prior works on Internet services only focus on the security of an individual network layer in isolation, whereas the adversaries do quite the opposite – they look for opportunities to exploit the interactions across heterogeneous components and layers to compromise the system security.

Neural Knowledge Representation and Reasoning

Duke Computer Science Colloquium
Speaker Name
Patrick Verga
Location
LSRC D106
Date and Time
-

Making complex decisions in areas like science, government policy, finance, and clinical treatments all require integrating and reasoning over disparate data sources. While some decisions can be made from a single source of information, others require considering multiple pieces of evidence and how they relate to one another.

MS Defense

Master's Defense
Speaker Name
Cheng Chen
Location
LSRC D344
Date and Time
-

MS Defense

Master's Defense
Speaker Name
Trung Tran
Location
LSRC D344
Date and Time
-

PhD Defense

Ph. D. Defense
Speaker Name
Brett Walenz
Location
LSRC D344
Date and Time
-