The success of generative modeling in continuous domains has led to a surge of interest in generating discrete data such as molecules, source code, and graphs. However, construction histories for these discrete objects are typically not unique and so generative models must reason about intractably large spaces in order to learn. Additionally, structured discrete domains are often characterized by strict constraints on what constitutes a valid object and generative models must respect these requirements in order to produce useful novel samples. Here, we present a generative model for discrete objects employing a Markov chain where transitions are restricted to a set of local operations that preserve validity.

This post demonstrate the use of code snippets in the theme. The code snippets are powered by Pygments and the code theme that is been used in Reverie is called Draula.

Sometimes, your post just stands for itself and doesn’t need a title. And that’s fine, too!

Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce bibendum neque eget nunc mattis eu sollicitudin enim tincidunt. Vestibulum lacus tortor, ultricies id dignissim ac, bibendum in velit. Praesent varius interdum vehicula. Aenean risus libero, placerat at vestibulum eget, ultricies eu enim. Praesent nulla tortor, malesuada adipiscing adipiscing sollicitudin, adipiscing eget est.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Fusce bibendum neque eget nunc mattis eu sollicitudin enim tincidunt. Vestibulum lacus tortor, ultricies id dignissim ac, bibendum in velit. Proin convallis mi ac felis pharetra aliquam. Curabitur dignissim accumsan rutrum. In arcu magna, aliquet vel pretium et, molestie et arcu. Mauris lobortis nulla et felis ullamcorper bibendum. Phasellus et hendrerit mauris. Proin eget nibh a massa vestibulum pretium. Suspendisse eu nisl a ante aliquet bibendum quis a nunc. Praesent varius interdum vehicula. Aenean risus libero, placerat at vestibulum eget, ultricies eu enim. Praesent nulla tortor, malesuada adipiscing adipiscing sollicitudin, adipiscing eget est.

It only barely fit through the door -- required some reversible repairs to the doorframe and nearby sheetrock -- but we got it in. 150 watt Boss CO2.

• 

• 

• 

We consider optimization problems in which the objective requires an inner loop with many steps or is the limit of a sequence of increasingly costly approximations. Meta-learning, training recurrent neural networks, and optimization of the solutions to differential equations are all examples of optimization problems with this character. In such problems, it can be expensive to compute the objective function value and its gradient, but truncating the loop or using less accurate approximations can induce biases that damage the overall solution. We propose randomized telescope (RT) gradient estimators, which represent the objective as the sum of a telescoping series and sample linear combinations of terms to provide cheap unbiased gradient estimates.

The university safety folks said we needed to have serious ventilation and fire suppression, even for consumer-grade FDM 3D-printers. The enclosures do look cool, though.

The lab is now (mostly) complete! The first piece of equipment just arrived: a Tormach 1100M. It's a bit of a toy in the machining world, but it's about the only thing that would fit in the CS building freight elevator and through the door. Even the Haas MiniMill isn't mini enough to make it to the fourth floor.

• 

• 

• 

• 

• 

• 

•