Upcoming Events

The theory of approximate optimization faces new challenges and opportunities thanks to its increasing interaction with other fields of optimization. Such growth and diversity call for a unified theory of approximate optimization, where various algorithms and complexity results can be connected to one another and explained by a few general principles. My research aims to contribute to such a theory, by building a unified theory for general classes of optimization problems and exploring connections between such classes. This talk will showcase results in both directions. 

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.

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.

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.

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. 

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.

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.

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.

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.

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.

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”).

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 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.

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.