Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

121242362483 · Jun 202019922001200920182026
48 results for Machine Teaching

The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch between the demand for machine learning systems and the ability for organizations to b…

2017-07-21abs ↗pdf ↗

In this paper, we consider the problem of machine teaching, the inverse problem of machine learning. Different from traditional machine teaching which views the learners as batch algorithms, we study a new paradigm where the learner uses an iterative algorithm and a teacher can feed examples sequentially and intelligen…

2017-05-30abs ↗pdf ↗

A collaborative machine teaching method that improves learner performance with privacy and efficiency.

problem Improving learner performance with distributed teachers while maintaining privacy and scalability.
method Formulates collaborative teaching as a consensus and privacy-preserving optimization process to minimize teaching risk.
result The proposed method delivers significantly more accurate teaching results with high speed compared to non-collaborative MINLP-based super teaching.

Optimal control theory improves machine teaching efficiency.

problem Finding the shortest training sequence for a sequential learning algorithm to reach a target model.
method Formulated as a time-optimal control problem, leveraging optimal control theory and computational tools.
result Optimal training sequences can vastly outperform existing heuristics.

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner's model. In such scenario, we study how the teacher is still able to …

2017-10-21abs ↗pdf ↗

Compared to machines, humans are extremely good at classifying images into categories, especially when they possess prior knowledge of the categories at hand. If this prior information is not available, supervision in the form of teaching images is required. To learn categories more quickly, people should see important…

2015-04-28abs ↗pdf ↗

Teaches AI models to learn effectively through dynamic loss functions.

problem Optimizing machine learning models' performance through dynamic loss functions.
method Develops a method for a teacher model to dynamically output loss functions for a student model, enabling gradient-based optimization.
result Significantly improves the performance of various student models in real-world tasks.

Teaches diverse students in a classroom setting with minimal examples.

problem Teaching a diverse group of students with varying initial states and learning rates.
method Proves an optimal teaching strategy with O(min{d,N} log(1/eps)) examples, robust to limited knowledge, and studies workload-cost trade-offs.
result Teaching a target concept to the entire classroom using optimal number of examples, validated by experiments.

Improves learning efficiency for active sequential learners.

problem Optimizing training data for sequential learners who actively choose their queries.
method Formulated as a Markov decision process, addressing both teaching and learning from a teacher.
result Planning teaching and learner's model of the teacher improve learning outcomes.

We study the problem of computer-assisted teaching with explanations. Conventional approaches for machine teaching typically only provide feedback at the instance level e.g., the category or label of the instance. However, it is intuitive that clear explanations from a knowledgeable teacher can significantly improve a …

2018-02-20abs ↗pdf ↗

Study on teaching reinforcement learning with Q-learning, reducing sample complexity.

problem Reducing sample complexity in reinforcement learning.
method Characterized teaching dimension for Q-learning under different teacher control, presented optimal teaching algorithms.
result Minimum number of samples needed for reinforcement learning is characterized.

Average teaching complexity for locating target regions among halfspace intersections is Θ(d).

problem Teaching the location of a target region among intersections of halfspaces.
method Novel insights from computational geometry to count convex polytopes and faces.
result Average-case teaching complexity is Θ(d), contrasting with Θ(n) worst-case complexity.

Study finds flipped classrooms improve student self-concept, enjoyment, but not exam scores.

problem Evaluating the impact of flipped classrooms on higher education outcomes.
method Double/debiased machine learning (DML) approach to analyze student data.
result No significant positive effects on exam scores, passing rates, or knowledge retention.

Develops counterfactual visual explanations to show how images could change to classify differently.

problem Creating understandable explanations for vision system predictions.
method Selects a distractor image and identifies spatial regions to modify for different classification.
result Users trained with counterfactual explanations perform better in fine-grained bird classification.

Paper improves teaching by considering learner's preferences and constraints.

problem Teaching without considering learner's preferences and constraints.
method Design of learner-aware teaching algorithms that account for learner's preferences and constraints.
result Significant performance improvements over learner-agnostic teaching.

XGL uses global explanations to guide human supervision in machine learning.

problem Improving model quality through human-machine interaction.
method XGL employs global explanations to guide human selection of informative examples.
result XGL avoids overselling the model's quality and performs comparably to other strategies.

We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static policy, we focus on the teacher as a decision maker who can dynamically choose differ…

2012-10-16abs ↗pdf ↗

TED framework teaches AI to explain decisions, improving accuracy.

problem Providing understandable explanations for AI predictions in high-stakes applications.
method Augmenting training data with explanations from domain users, using embeddings and multi-task learning.
result AI models can be taught to provide meaningful explanations, sometimes improving accuracy.

Study on teaching complexity in graphs, proving hardness and tractability.

problem Computing the minimum number of examples per concept for teaching.
method Classical and parameterized complexity analysis, NP-hardness, upper and lower bounds, fixed-parameter tractability.
result Nearly complete understanding of teaching complexity in graphs.

Paper tackles inverse reinforcement learning with feature mismatch, proposing a teaching scheme.

problem Learning near-optimal behavior from an expert's demonstrations when there's a mismatch between the learner and expert's worldviews.
method Introduces teaching risk to measure suboptimality and suggests a teaching scheme to decrease it.
result Standard algorithms based on inverse reinforcement learning can find near-optimal policies with bounds on teaching risk.

The paper teaches machines to ask clarifying questions by applying NLI.

problem Teaching machines to ask clarifying questions for better comprehension.
method The approach is to use NLI to determine if a clarification question is about a missing piece of information in a post.
result The best model improved precision@1 by 40% and 60% over state-of-the-art baselines.

This work proves lower bounds on a greedy teaching set construction algorithm.

problem Characterize the best-case teaching dimension of a concept class.
method A greedy algorithm that iteratively adds points to the teaching set to restrict the concept class the most.
result Lower bounds on the performance of the greedy approach for small k, extending up to k ≤ c*d for small constant c.

Interactive teaching speeds up IRL learning with adaptive demonstrations.

problem Tackles the challenge of accelerating IRL learning with teacher assistance.
method Interactive teaching framework where a teacher adapts demonstrations based on the learner's policy.
result Teaching algorithms converge in the omniscient setting, speeding up learning.

Semi-supervised wrapper methods are concerned with building effective supervised classifiers from partially labeled data. Though previous works have succeeded in some fields, it is still difficult to apply semi-supervised wrapper methods to practice because the assumptions those methods rely on tend to be unrealistic i…

2016-11-12abs ↗pdf ↗

This work introduces reward teaching for federated multi-armed bandits to guide clients towards global optimality.

problem Existing federated multi-armed bandits designs assume clients will follow the server's protocol, but this is not always feasible.
method Introduces reward teaching where the server adjusts clients' local rewards to encourage global optimality, using phased Teaching-After-Learning (TAL) and Teaching-While-Learning (TWL) algorithms.
result Demonstrates that TAL achieves logarithmic regrets with only logarithmic adjustment costs, and TWL outperforms TAL for UCB1 clients.

The ability to use a 2D map to navigate a complex 3D environment is quite remarkable, and even difficult for many humans. Localization and navigation is also an important problem in domains such as robotics, and has recently become a focus of the deep reinforcement learning community. In this paper we teach a reinforce…

2017-11-20abs ↗pdf ↗

Learning with noisy labels is one of the hottest problems in weakly-supervised learning. Based on memorization effects of deep neural networks, training on small-loss instances becomes very promising for handling noisy labels. This fosters the state-of-the-art approach "Co-teaching" that cross-trains two deep neural ne…

2019-01-14abs ↗pdf ↗