19 citations · 123 across the 25 of their papers we have counts for
29 papers
Adversarial Attacks on Combinatorial Multi-Armed Bandits
Rishab Balasubramanian, Jiawei Li, Prasad Tadepalli +3
We study reward poisoning attacks on Combinatorial Multi-armed Bandits (CMAB). We first provide a sufficient and necessary condition for the attackability of CMAB, a notion to capt…
Explainable Models via Compression of Tree Ensembles
Siwen Yan, Sriraam Natarajan, Saket Joshi +2
Ensemble models (bagging and gradient-boosting) of relational decision trees have proved to be one of the most effective learning methods in the area of probabilistic logic models…
Parametrically Retargetable Decision-Makers Tend To Seek Power
Alexander Matt Turner, Prasad Tadepalli
If capable AI agents are generally incentivized to seek power in service of the objectives we specify for them, then these systems will pose enormous risks, in addition to enormous…
Formalizing the Problem of Side Effect Regularization
Alexander Matt Turner, Aseem Saxena, Prasad Tadepalli
AI objectives are often hard to specify properly. Some approaches tackle this problem by regularizing the AI's side effects: Agents must weigh off "how much of a mess they make" wi…
Dynamic probabilistic logic models for effective abstractions in RL
Harsha Kokel, Arjun Manoharan, Sriraam Natarajan +2
State abstraction enables sample-efficient learning and better task transfer in complex reinforcement learning environments. Recently, we proposed RePReL (Kokel et al. 2021), a hie…
From Heatmaps to Structural Explanations of Image Classifiers
Li Fuxin, Zhongang Qi, Saeed Khorram +4
This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained. The pape…
Improving Multilingual Translation by Representation and Gradient Regularization
Yilin Yang, Akiko Eriguchi, Alexandre Muzio +3
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Des…
One Explanation is Not Enough: Structured Attention Graphs for Image Classification
Vivswan Shitole, Li Fuxin, Minsuk Kahng +2
Attention maps are a popular way of explaining the decisions of convolutional networks for image classification. Typically, for each image of interest, a single attention map is pr…
On the Sub-Layer Functionalities of Transformer Decoder
Yilin Yang, Longyue Wang, Shuming Shi +3
There have been significant efforts to interpret the encoder of Transformer-based encoder-decoder architectures for neural machine translation (NMT); meanwhile, the decoder remains…
DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
Aayam Shrestha, Stefan Lee, Prasad Tadepalli +1
We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be a…
Avoiding Side Effects in Complex Environments
Alexander Matt Turner, Neale Ratzlaff, Prasad Tadepalli
Reward function specification can be difficult. Rewarding the agent for making a widget may be easy, but penalizing the multitude of possible negative side effects is hard. In toy…
Relation Extraction with Explanation
Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini +1
Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Effort…
Optimal Policies Tend to Seek Power
Alexander Matt Turner, Logan Smith, Rohin Shah +2
Some researchers speculate that intelligent reinforcement learning (RL) agents would be incentivized to seek resources and power in pursuit of their objectives. Other researchers p…
The Choice Function Framework for Online Policy Improvement
Murugeswari Issakkimuthu, Alan Fern, Prasad Tadepalli
There are notable examples of online search improving over hand-coded or learned policies (e.g. AlphaZero) for sequential decision making. It is not clear, however, whether or not…
Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation
Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini +2
We present a new local entity disambiguation system. The key to our system is a novel approach for learning entity representations. In our approach we learn an entity aware extensi…
Saliency Learning: Teaching the Model Where to Pay Attention
Reza Ghaeini, Xiaoli Z. Fern, Hamed Shahbazi +1
Deep learning has emerged as a compelling solution to many NLP tasks with remarkable performances. However, due to their opacity, such models are hard to interpret and trust. Recen…
Conservative Agency via Attainable Utility Preservation
Alexander Matt Turner, Dylan Hadfield-Menell, Prasad Tadepalli
Reward functions are easy to misspecify; although designers can make corrections after observing mistakes, an agent pursuing a misspecified reward function can irreversibly change…
Interactive Naming for Explaining Deep Neural Networks: A Formative Study
Mandana Hamidi-Haines, Zhongang Qi, Alan Fern +2
We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of…
Learning Scripts as Hidden Markov Models
J. Walker Orr, Prasad Tadepalli, Janardhan Rao Doppa +2
Scripts have been proposed to model the stereotypical event sequences found in narratives. They can be applied to make a variety of inferences including filling gaps in the narrati…
Attentional Multi-Reading Sarcasm Detection
Reza Ghaeini, Xiaoli Z. Fern, Prasad Tadepalli
Recognizing sarcasm often requires a deep understanding of multiple sources of information, including the utterance, the conversational context, and real world facts. Most of the c…
Event Detection with Neural Networks: A Rigorous Empirical Evaluation
J. Walker Orr, Prasad Tadepalli, Xiaoli Fern
Detecting events and classifying them into predefined types is an important step in knowledge extraction from natural language texts. While the neural network models have generally…
Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference
Reza Ghaeini, Xiaoli Z. Fern, Prasad Tadepalli
Deep learning models have achieved remarkable success in natural language inference (NLI) tasks. While these models are widely explored, they are hard to interpret and it is often…
Joint Neural Entity Disambiguation with Output Space Search
Hamed Shahbazi, Xiaoli Z. Fern, Reza Ghaeini +3
In this paper, we present a novel model for entity disambiguation that combines both local contextual information and global evidences through Limited Discrepancy Search (LDS). Giv…
Dependent Gated Reading for Cloze-Style Question Answering
Reza Ghaeini, Xiaoli Z. Fern, Hamed Shahbazi +1
We present a novel deep learning architecture to address the cloze-style question answering task. Existing approaches employ reading mechanisms that do not fully exploit the interd…