Search Results for author:
Found 72 papers, 28 papers with code
Quantifying and Improving Transferability in Domain Generalization
We then prove that our transferability can be estimated with enough samples and give a new upper bound for the target error based on our transferability.
SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networks
We introduce SPFlow, an open-source Python library providing a simple interface to inference, learning and manipulation routines for deep and tractable probabilistic models called Sum-Product Networks (SPNs).
Time2Vec: Learning a Vector Representation of Time
Time is an important feature in many applications involving events that occur synchronously and/or asynchronously.
Matrix Nets: A New Deep Architecture for Object Detection
We present Matrix Nets (xNets), a new deep architecture for object detection.
Ranked #97 on
Object Detection
on COCO test-dev
MatrixNets: A New Scale and Aspect Ratio Aware Architecture for Object Detection
We present MatrixNets (xNets), a new deep architecture for object detection.
Diachronic Embedding for Temporal Knowledge Graph Completion
In this paper, we build novel models for temporal KG completion through equipping static models with a diachronic entity embedding function which provides the characteristics of entities at any point in time.
Variational Attention for Sequence-to-Sequence Models
The variational encoder-decoder (VED) encodes source information as a set of random variables using a neural network, which in turn is decoded into target data using another neural network.
Unsupervised Video Object Segmentation for Deep Reinforcement Learning
The detection of moving objects is done in an unsupervised way by exploiting structure from motion.
Learning Dynamic Belief Graphs to Generalize on Text-Based Games
Playing text-based games requires skills in processing natural language and sequential decision making.
FedFormer: Contextual Federation with Attention in Reinforcement Learning
We evaluate our methods on the Meta-World environment and find that our approach yields significant improvements over FedAvg and non-federated Soft Actor-Critic single-agent methods.
Multi Type Mean Field Reinforcement Learning
We consider two different kinds of mean field environments: a) Games where agents belong to predefined types that are known a priori and b) Games where the type of each agent is unknown and therefore must be learned based on observations.
NTS-NOTEARS: Learning Nonparametric DBNs With Prior Knowledge
We describe NTS-NOTEARS, a score-based structure learning method for time-series data to learn dynamic Bayesian networks (DBNs) that captures nonlinear, lagged (inter-slice) and instantaneous (intra-slice) relations among variables.
Progressive Memory Banks for Incremental Domain Adaptation
The memory bank provides a natural way of IDA: when adapting our model to a new domain, we progressively add new slots to the memory bank, which increases the number of parameters, and thus the model capacity.
Online Structure Learning for Sum-Product Networks with Gaussian Leaves
Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable.
Benchmarking Constraint Inference in Inverse Reinforcement Learning
When deploying Reinforcement Learning (RL) agents into a physical system, we must ensure that these agents are well aware of the underlying constraints.
Unsupervised Multilingual Alignment using Wasserstein Barycenter
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data.
Ranked #1 on
Word Alignment
on en-es
A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?
Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space.
Partially Observable Mean Field Reinforcement Learning
Traditional multi-agent reinforcement learning algorithms are not scalable to environments with more than a few agents, since these algorithms are exponential in the number of agents.
Multi-agent Reinforcement Learning
Q-Learning
Multiagent Systems
WatClaimCheck: A new Dataset for Claim Entailment and Inference
We contribute a new dataset for the task of automated fact checking and an evaluation of state of the art algorithms.
Order-Planning Neural Text Generation From Structured Data
Generating texts from structured data (e. g., a table) is important for various natural language processing tasks such as question answering and dialog systems.
Newton-type Methods for Minimax Optimization
We prove their local convergence at strict local minimax points, which are surrogates of global solutions.
On Improving Deep Reinforcement Learning for POMDPs
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e. g., computer Go.
Learning Functions on Multiple Sets using Multi-Set Transformers
We propose a general deep architecture for learning functions on multiple permutation-invariant sets.
Robust One Round Federated Learning with Predictive Space Bayesian Inference
In contrast, our method performs the aggregation on the predictive posteriors, which are typically easier to approximate owing to the low-dimensionality of the output space.
On Improving Deep Reinforcement Learning for POMDPs
Deep Reinforcement Learning (RL) recently emerged as one of the most competitive approaches for learning in sequential decision making problems with fully observable environments, e. g., computer Go.
Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
This paper addresses the question: Why do neural dialog systems generate short and meaningless replies?
Affective Neural Response Generation
Existing neural conversational models process natural language primarily on a lexico-syntactic level, thereby ignoring one of the most crucial components of human-to-human dialogue: its affective content.
Deep Active Learning for Dialogue Generation
We propose an online, end-to-end, neural generative conversational model for open-domain dialogue.
Generative Mixture of Networks
The model consists of K networks that are trained together to learn the underlying distribution of a given data set.
Discovering Conversational Dependencies between Messages in Dialogs
We investigate the task of inferring conversational dependencies between messages in one-on-one online chat, which has become one of the most popular forms of customer service.
Online and Distributed learning of Gaussian mixture models by Bayesian Moment Matching
The Gaussian mixture model is a classic technique for clustering and data modeling that is used in numerous applications.
A Unified Approach for Learning the Parameters of Sum-Product Networks
We present a unified approach for learning the parameters of Sum-Product networks (SPNs).
Dynamic Sum Product Networks for Tractable Inference on Sequence Data (Extended Version)
Since SPNs represent distributions over a fixed set of variables only, we propose dynamic sum product networks (DSPNs) as a generalization of SPNs for sequence data of varying length.
On the Relationship between Sum-Product Networks and Bayesian Networks
We conclude the paper with some discussion of the implications of the proof and establish a connection between the depth of an SPN and a lower bound of the tree-width of its corresponding BN.
Self-Adaptive Hierarchical Sentence Model
The ability to accurately model a sentence at varying stages (e. g., word-phrase-sentence) plays a central role in natural language processing.
Ranked #5 on
Subjectivity Analysis
on SUBJ
A Sober Look at Spectral Learning
In contrast, maximum likelihood estimates may get trapped in local optima due to the non-convex nature of the likelihood function of latent variable models.
Exploiting Structure in Weighted Model Counting Approaches to Probabilistic Inference
Previous studies have demonstrated that encoding a Bayesian network into a SAT formula and then performing weighted model counting using a backtracking search algorithm can be an effective method for exact inference.
Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks
Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable.
Deep Homogeneous Mixture Models: Representation, Separation, and Approximation
At their core, many unsupervised learning models provide a compact representation of homogeneous density mixtures, but their similarities and differences are not always clearly understood.
Monte-Carlo Tree Search for Constrained POMDPs
In this paper, we present CC-POMCP (Cost-Constrained POMCP), an online MCTS algorithm for large CPOMDPs that leverages the optimization of LP-induced parameters and only requires a black-box simulator of the environment.
Online Bayesian Moment Matching for Topic Modeling with Unknown Number of Topics
When the number of topics (or latent groups) is unknown, the Hierarchical Dirichlet Process (HDP) provides an elegant non-parametric extension; however, it is a complex model and it is difficult to incorporate prior knowledge since the distribution over topics is implicit.
Symbolic Dynamic Programming for Continuous State and Observation POMDPs
In recent years, point- based value iteration methods have proven to be extremely effective techniques for finding (approximately) optimal dynamic programming solutions to POMDPs when an initial set of belief states is known.
Cost-Sensitive Exploration in Bayesian Reinforcement Learning
In this paper, we consider Bayesian reinforcement learning (BRL) where actions incur costs in addition to rewards, and thus exploration has to be constrained in terms of the expected total cost while learning to maximize the expected long-term total reward.
Automated Refinement of Bayes Networks' Parameters based on Test Ordering Constraints
We demonstrate that consistency with an expert's test selection leads to non-convex constraints on the model parameters.
Representation Learning for Dynamic Graphs: A Survey
Graphs arise naturally in many real-world applications including social networks, recommender systems, ontologies, biology, and computational finance.
Comparing EM with GD in Mixture Models of Two Components
In the case of mixtures of Bernoullis, we find that there exist one-cluster regions that are stable for GD and therefore trap GD, but those regions are unstable for EM, allowing EM to escape.
Batch norm with entropic regularization turns deterministic autoencoders into generative models
The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input.
Optimality and Stability in Non-Convex Smooth Games
Convergence to a saddle point for convex-concave functions has been studied for decades, while recent years has seen a surge of interest in non-convex (zero-sum) smooth games, motivated by their recent wide applications.
Generating Emotionally Aligned Responses in Dialogues using Affect Control Theory
State-of-the-art neural dialogue systems excel at syntactic and semantic modelling of language, but often have a hard time establishing emotional alignment with the human interactant during a conversation.
A Positivstellensatz for Conditional SAGE Signomials
Recently, the conditional SAGE certificate has been proposed as a sufficient condition for signomial positivity over a convex set.
Online Bayesian Moment Matching based SAT Solver Heuristics
Our solvers out-perform the baselines by solving 12 more instances from the SAT competition 2018 application benchmark and are %40 faster on average in solving hard cryptographic instances.
Learning Agent Representations for Ice Hockey
This paper develops a new approach for agent representations, based on a Markov game model, that is tailored towards applications in professional ice hockey.
Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning
In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort.
Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map
While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed.
Robust Embeddings Via Distributions
Despite recent monumental advances in the field, many Natural Language Processing (NLP) models still struggle to perform adequately on noisy domains.
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
To address these problems, we propose a RAndom Intermediate Layer Knowledge Distillation (RAIL-KD) approach in which, intermediate layers from the teacher model are selected randomly to be distilled into the intermediate layers of the student model.
Distributional Reinforcement Learning with Monotonic Splines
Distributional Reinforcement Learning (RL) differs from traditional RL by estimating the distribution over returns to capture the intrinsic uncertainty of MDPs.
Distributional Reinforcement Learning
reinforcement-learning
+1
Learning Object-Oriented Dynamics for Planning from Text
The advancement of dynamics models enables model-based planning in complex environments.
Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning
We propose a Represent And Mimic (RAMi) framework for training 1) an identifiable latent representation to capture the independent factors of variation for the objects and 2) a mimic tree that extracts the causal impact of the latent features on DRL action values.
Physics Constrained Flow Neural Network for Short-Timescale Predictions in Data Communications Networks
Machine learning is gaining growing momentum in various recent models for the dynamic analysis of information flows in data communications networks.
CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation
Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models.
Do we need Label Regularization to Fine-tune Pre-trained Language Models?
Knowledge Distillation (KD) is a prominent neural model compression technique that heavily relies on teacher network predictions to guide the training of a student model.
Learning Soft Constraints From Constrained Expert Demonstrations
We consider the setting where the reward function is given, and the constraints are unknown, and propose a method that is able to recover these constraints satisfactorily from the expert data.
Federated Bayesian Neural Regression: A Scalable Global Federated Gaussian Process
We present Federated Bayesian Neural Regression (FedBNR), an algorithm that learns a scalable stand-alone global federated GP that respects clients' privacy.
Label Alignment Regularization for Distribution Shift
Recent work has highlighted the label alignment property (LAP) in supervised learning, where the vector of all labels in the dataset is mostly in the span of the top few singular vectors of the data matrix.
Continuation KD: Improved Knowledge Distillation through the Lens of Continuation Optimization
Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowledge from a larger model (a teacher).
Attribute Controlled Dialogue Prompting
Prompt-tuning has become an increasingly popular parameter-efficient method for adapting large pretrained language models to downstream tasks.
Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks
For instance, ReLU networks - a popular class of neural network architectures - have been shown to almost always yield high confidence predictions when the test data are far away from the training set, even when they are trained with OOD data.
Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space
To improve scalability for larger models, one common Bayesian approach is to approximate the global predictive posterior by multiplying local predictive posteriors.
Why Online Reinforcement Learning is Causal
Our main argument is that in online learning, conditional probabilities are causal, and therefore offline RL is the setting where causal learning has the most potential to make a difference.
A Simple Mixture Policy Parameterization for Improving Sample Efficiency of CVaR Optimization
Reinforcement learning algorithms utilizing policy gradients (PG) to optimize Conditional Value at Risk (CVaR) face significant challenges with sample inefficiency, hindering their practical applications.
