Search Results for author:
Found 35 papers, 11 papers with code
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement
Models pretrained on ImageNet+ and fine-tuned on CIFAR-100+, Flowers-102+, and Food-101+, reach up to 3. 4% improved accuracy.
An Empirical Study of Implicit Regularization in Deep Offline RL
Also, we empirically identify three phases of learning that explain the impact of implicit regularization on the learning dynamics and found that bootstrapping alone is insufficient to explain the collapse of the effective rank.
Continual Learning Beyond a Single Model
A growing body of research in continual learning focuses on the catastrophic forgetting problem.
Architecture Matters in Continual Learning
However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.
Wide Neural Networks Forget Less Catastrophically
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts.
Task-agnostic Continual Learning with Hybrid Probabilistic Models
Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning.
Balance Regularized Neural Network Models for Causal Effect Estimation
Estimating individual and average treatment effects from observational data is an important problem in many domains such as healthcare and e-commerce.
Linear Mode Connectivity in Multitask and Continual Learning
Continual (sequential) training and multitask (simultaneous) training are often attempting to solve the same overall objective: to find a solution that performs well on all considered tasks.
The Effectiveness of Memory Replay in Large Scale Continual Learning
However, a degraded performance is observed for ER with small memory.
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
This problem is often referred to as catastrophic forgetting, a key challenge in continual learning of neural networks.
A maximum-entropy approach to off-policy evaluation in average-reward MDPs
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs).
Understanding the Role of Training Regimes in Continual Learning
However, there has been limited prior work extensively analyzing the impact that different training regimes -- learning rate, batch size, regularization method-- can have on forgetting.
Learning to Incentivize Other Learning Agents
The challenge of developing powerful and general Reinforcement Learning (RL) agents has received increasing attention in recent years.
Dropout as an Implicit Gating Mechanism For Continual Learning
However, it is more reliable to preserve the knowledge it has learned from the previous tasks.
Self-Distillation Amplifies Regularization in Hilbert Space
Knowledge distillation introduced in the deep learning context is a method to transfer knowledge from one architecture to another.
Orthogonal Gradient Descent for Continual Learning
In this paper, we propose to address this issue from a parameter space perspective and study an approach to restrict the direction of the gradient updates to avoid forgetting previously-learned data.
Cross-View Policy Learning for Street Navigation
The ability to navigate from visual observations in unfamiliar environments is a core component of intelligent agents and an ongoing challenge for Deep Reinforcement Learning (RL).
DyRep: Learning Representations over Dynamic Graphs
We present DyRep - a novel modeling framework for dynamic graphs that posits representation learning as a latent mediation process bridging two observed processes namely -- dynamics of the network (realized as topological evolution) and dynamics on the network (realized as activities between nodes).
Improved Knowledge Distillation via Teacher Assistant
To alleviate this shortcoming, we introduce multi-step knowledge distillation, which employs an intermediate-sized network (teacher assistant) to bridge the gap between the student and the teacher.
Adapting Auxiliary Losses Using Gradient Similarity
One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations.
Representation Learning over Dynamic Graphs
How can we effectively encode evolving information over dynamic graphs into low-dimensional representations?
More Robust Doubly Robust Off-policy Evaluation
In particular, we focus on the doubly robust (DR) estimators that consist of an importance sampling (IS) component and a performance model, and utilize the low (or zero) bias of IS and low variance of the model at the same time.
Hawkes Processes for Invasive Species Modeling and Management
The spread of invasive species to new areas threatens the stability of ecosystems and causes major economic losses in agriculture and forestry.
Wasserstein Learning of Deep Generative Point Process Models
Point processes are becoming very popular in modeling asynchronous sequential data due to their sound mathematical foundation and strength in modeling a variety of real-world phenomena.
Joint Modeling of Event Sequence and Time Series with Attentional Twin Recurrent Neural Networks
A variety of real-world processes (over networks) produce sequences of data whose complex temporal dynamics need to be studied.
Fake News Mitigation via Point Process Based Intervention
We propose the first multistage intervention framework that tackles fake news in social networks by combining reinforcement learning with a point process network activity model.
Recurrent Poisson Factorization for Temporal Recommendation
Poisson factorization is a probabilistic model of users and items for recommendation systems, where the so-called implicit consumer data is modeled by a factorized Poisson distribution.
Distilling Information Reliability and Source Trustworthiness from Digital Traces
Then, we propose a temporal point process modeling framework that links these temporal traces to robust, unbiased and interpretable notions of information reliability and source trustworthiness.
Smart broadcasting: Do you want to be seen?
Many users in online social networks are constantly trying to gain attention from their followers by broadcasting posts to them.
Detecting weak changes in dynamic events over networks
Large volume of networked streaming event data are becoming increasingly available in a wide variety of applications, such as social network analysis, Internet traffic monitoring and healthcare analytics.
Learning Granger Causality for Hawkes Processes
In this paper, we propose an effective method, learning Granger causality, for a special but significant type of point processes --- Hawkes process.
A Continuous-time Mutually-Exciting Point Process Framework for Prioritizing Events in Social Media
In our experiments, we demonstrate that our algorithm is able to achieve the-state-of-the-art performance in terms of analyzing, predicting, and prioritizing events.
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
Information diffusion in online social networks is affected by the underlying network topology, but it also has the power to change it.
Shaping Social Activity by Incentivizing Users
Events in an online social network can be categorized roughly into endogenous events, where users just respond to the actions of their neighbors within the network, or exogenous events, where users take actions due to drives external to the network.
From Local Similarity to Global Coding: An Application to Image Classification
Exploiting the local similarity of a descriptor and its nearby bases, a global measure of association of a descriptor to all the bases is computed.
