Search Results for author:
Found 15 papers, 3 papers with code
Every Model Learned by Gradient Descent Is Approximately a Kernel Machine
Deep learning's successes are often attributed to its ability to automatically discover new representations of the data, rather than relying on handcrafted features like other learning methods.
Amodal 3D Reconstruction for Robotic Manipulation via Stability and Connectivity
By using these priors over the physical properties of objects, our system improves reconstruction quality not just by standard visual metrics, but also performance of model-based control on a variety of robotics manipulation tasks in challenging, cluttered environments.
Relevance-Guided Modeling of Object Dynamics for Reinforcement Learning
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency.
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
Recent studies in cognitive science, artificial intelligence, and psychology have produced a number of cognitive models of reasoning, learning, and language that are underpinned by computation.
Deep Learning as a Mixed Convex-Combinatorial Optimization Problem
Based on this, we develop a recursive mini-batch algorithm for learning deep hard-threshold networks that includes the popular but poorly justified straight-through estimator as a special case.
The Sum-Product Theorem: A Foundation for Learning Tractable Models
We illustrate the power and generality of this approach by applying it to a new type of structured prediction problem: learning a nonconvex function that can be globally optimized in polynomial time.
Recursive Decomposition for Nonconvex Optimization
Similarly to DPLL-style SAT solvers and recursive conditioning in probabilistic inference, our algorithm, RDIS, recursively sets variables so as to simplify and decompose the objective function into approximately independent sub-functions, until the remaining functions are simple enough to be optimized by standard techniques like gradient descent.
On the Latent Variable Interpretation in Sum-Product Networks
We discuss conditional independencies in augmented SPNs, formally establish the probabilistic interpretation of the sum-weights and give an interpretation of augmented SPNs as Bayesian networks.
Learning Tractable Probabilistic Models for Fault Localization
While most previous statistical debugging methods generalize over many executions of a single program, TFLMs are trained on a corpus of previously seen buggy programs, and learn to identify recurring patterns of bugs.
Exchangeable Variable Models
A sequence of random variables is exchangeable if its joint distribution is invariant under variable permutations.
Structured Message Passing
In this paper, we present structured message passing (SMP), a unifying framework for approximate inference algorithms that take advantage of structured representations such as algebraic decision diagrams and sparse hash tables.
Sum-Product Networks: A New Deep Architecture
Experiments show that inference and learning with SPNs can be both faster and more accurate than with standard deep networks.
Learning Efficient Markov Networks
We present an algorithm for learning high-treewidth Markov networks where inference is still tractable.
Approximate Inference by Compilation to Arithmetic Circuits
Arithmetic circuits (ACs) exploit context-specific independence and determinism to allow exact inference even in networks with high treewidth.
