Search Results for author:
Found 65 papers, 28 papers with code
Density Measures for Language Generation
A recent line of work proposes an abstract view, called language generation in the limit, where generation is seen as a game between an adversary and an algorithm: the adversary generates strings from an unknown language $K$, chosen from a countable collection of candidate languages, and after seeing a finite set of these strings, the algorithm must generate new strings from $K$ that it has not seen before.
The Backfiring Effect of Weak AI Safety Regulation
In particular, we assume AI technology is described by two key attributes: safety and performance.
What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models
Many existing metrics focus on a model's producibility, i. e. the quality and breadth of outputs it can generate.
AI-Assisted Decision Making with Human Learning
As the algorithm becomes more "patient" or the human's learning improves, the algorithm increasingly selects more informative features, enhancing both prediction accuracy and the human's understanding.
Sparse Autoencoders for Hypothesis Generation
We describe HypotheSAEs, a general method to hypothesize interpretable relationships between text data (e. g., headlines) and a target variable (e. g., clicks).
A No Free Lunch Theorem for Human-AI Collaboration
The result does suggest one model of collaboration with guarantees, where one agent identifies "obvious" errors of the other agent.
Maia-2: A Unified Model for Human-AI Alignment in Chess
Previous work in modeling human decision-making in chess uses completely independent models to capture human style at different skill levels, meaning they lack coherence in their ability to adapt to the full spectrum of human improvement and are ultimately limited in their effectiveness as AI partners and teaching tools.
Evaluating the World Model Implicit in a Generative Model
Building generative models that meaningfully capture the underlying logic of the domains they model would be immensely valuable; our results suggest new ways to assess how close a given model is to that goal.
Designing Skill-Compatible AI: Methodologies and Frameworks in Chess
Traditional chess engines designed to output near-optimal moves prove to be inadequate partners when paired with engines of various lower skill levels in this domain, as they are not designed to consider the presence of other agents.
Language Generation in the Limit
A computational agent is trying to learn to generate from this language; we say that the agent generates from L in the limit if after some finite point in the enumeration of L, the agent is able to produce new elements that come exclusively from L and that have not yet been presented by the adversary.
Microstructures and Accuracy of Graph Recall by Large Language Models
Moreover, we find that more advanced LLMs have a striking dependence on the domain that a real-world graph comes from -- by yielding the best recall accuracy when the graph is narrated in a language style consistent with its original domain.
From Graphs to Hypergraphs: Hypergraph Projection and its Remediation
Such a modeling choice typically involves an underlying projection process that maps the original hypergraph onto a graph, and is common in graph-based analysis.
Strategic Evaluation: Subjects, Evaluators, and Society
Machine learning literature on strategic behavior has tried to describe these dynamics by emphasizing the efforts expended by decision subjects hoping to obtain a more favorable assessment -- some works offer ways to preempt or prevent such manipulations, some differentiate 'gaming' from 'improvement' behavior, while others aim to measure the effort burden or disparate effects of classification systems.
On the Actionability of Outcome Prediction
Through a simple model encompassing actions, latent states, and measurements, we demonstrate that pure outcome prediction rarely results in the most effective policy for taking actions, even when combined with other measurements.
Fine-Tuning Games: Bargaining and Adaptation for General-Purpose Models
We find that for a broad class of cost and revenue functions, there exists a set of Pareto-optimal profit-sharing arrangements where the players jointly contribute to the technology.
Reconciling the accuracy-diversity trade-off in recommendations
In recommendation settings, there is an apparent trade-off between the goals of accuracy (to recommend items a user is most likely to want) and diversity (to recommend items representing a range of categories).
Informational Diversity and Affinity Bias in Team Growth Dynamics
Prior work has provided strong evidence that, within organizational settings, teams that bring a diversity of information and perspectives to a task are more effective than teams that do not.
Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification.
Supervised Hypergraph Reconstruction
To reconstruct hypergraph data, we start by analyzing hyperedge distributions in the projection, based on which we create a framework containing two modules: (1) to handle the enormous search space of potential hyperedges, we design a sampling strategy with efficacy guarantees that significantly narrows the space to a smaller set of candidates; (2) to identify hyperedges from the candidates, we further design a hyperedge classifier in two well-working variants that capture structural features in the projection.
Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess
We present a transformer-based approach to behavioral stylometry in the context of chess, where one attempts to identify the player who played a set of games.
Mimetic Models: Ethical Implications of AI that Acts Like You
An emerging theme in artificial intelligence research is the creation of models to simulate the decisions and behavior of specific people, in domains including game-playing, text generation, and artistic expression.
Core-periphery Models for Hypergraphs
Our inference algorithm is capable of learning embeddings that correspond to the reputation (rank) of a node within the hypergraph.
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
More generally, the paper considers the learning of logical functions with gradient descent (GD) on neural networks.
Models of fairness in federated learning
These agents can collaborate to build a machine learning model based on data from multiple agents, potentially reducing the error each experiences.
Approximate Decomposable Submodular Function Minimization for Cardinality-Based Components
We develop the first approximation algorithms for this problem, where the approximations can be quickly computed via reduction to a sparse graph cut problem, with graph sparsity controlled by the desired approximation factor.
Pointer Value Retrieval: A new benchmark for understanding the limits of neural network generalization
In PVR, this is done by having one part of the task input act as a pointer, giving instructions on a different input location, which forms the output.
Using a Cross-Task Grid of Linear Probes to Interpret CNN Model Predictions On Retinal Images
We find that some target tasks are easily predicted irrespective of the source task, and that some other target tasks are more accurately predicted from correlated source tasks than from embeddings trained on the same task.
Optimality and Stability in Federated Learning: A Game-theoretic Approach
One branch of this research has taken a game-theoretic approach, and in particular, prior work has viewed federated learning as a hedonic game, where error-minimizing players arrange themselves into federating coalitions.
The Generalized Mean Densest Subgraph Problem
Finding dense subgraphs of a large graph is a standard problem in graph mining that has been studied extensively both for its theoretical richness and its many practical applications.
Allocating Opportunities in a Dynamic Model of Intergenerational Mobility
We develop a dynamic model for allocating such opportunities in a society that exhibits bottlenecks in mobility; the problem of optimal allocation reflects a trade-off between the benefits conferred by the opportunities in the current generation and the potential to elevate the socioeconomic status of recipients, shaping the composition of future generations in ways that can benefit further from the opportunities.
Computers and Society Physics and Society
Algorithmic Monoculture and Social Welfare
Here we show that the dangers of algorithmic monoculture run much deeper, in that monocultural convergence on a single algorithm by a group of decision-making agents, even when the algorithm is more accurate for any one agent in isolation, can reduce the overall quality of the decisions being made by the full collection of agents.
Model-sharing Games: Analyzing Federated Learning Under Voluntary Participation
Federated learning is a setting where agents, each with access to their own data source, combine models from local data to create a global model.
Learning Models of Individual Behavior in Chess
AI systems that can capture human-like behavior are becoming increasingly useful in situations where humans may want to learn from these systems, collaborate with them, or engage with them as partners for an extended duration.
Aligning Superhuman AI with Human Behavior: Chess as a Model System
We develop and introduce Maia, a customized version of Alpha-Zero trained on human chess games, that predicts human moves at a much higher accuracy than existing engines, and can achieve maximum accuracy when predicting decisions made by players at a specific skill level in a tuneable way.
Graphs over Time: Densification Laws, Shrinking Diameters and Possible Explanations
We provide a new graph generator, based on a "forest fire" spreading process, that has a simple, intuitive justification, requires very few parameters (like the "flammability" of nodes), and produces graphs exhibiting the full range of properties observed both in prior work and in the present study.
Adversarial Perturbations of Opinion Dynamics in Networks
We study the connections between network structure, opinion dynamics, and an adversary's power to artificially induce disagreements.
Data Structures and Algorithms Computer Science and Game Theory Social and Information Networks Physics and Society
Frozen Binomials on the Web: Word Ordering and Language Conventions in Online Text
These binomials are common across many areas of speech, in both formal and informal text.
Minimizing Localized Ratio Cut Objectives in Hypergraphs
However, there are only a few specialized approaches for localized clustering in hypergraphs.
Measuring the Completeness of Theories
We use machine learning to provide a tractable measure of the amount of predictable variation in the data that a theory captures, which we call its "completeness."
Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices
How are algorithmic assessments built, validated, and examined for bias?
Planted Hitting Set Recovery in Hypergraphs
In various application areas, networked data is collected by measuring interactions involving some specific set of core nodes.
The Algorithmic Automation Problem: Prediction, Triage, and Human Effort
In a wide array of areas, algorithms are matching and surpassing the performance of human experts, leading to consideration of the roles of human judgment and algorithmic prediction in these domains.
Transfusion: Understanding Transfer Learning for Medical Imaging
Investigating the learned representations and features, we find that some of the differences from transfer learning are due to the over-parametrization of standard models rather than sophisticated feature reuse.
Discrimination in the Age of Algorithms
But with appropriate requirements in place, the use of algorithms will make it possible to more easily examine and interrogate the entire decision process, thereby making it far easier to know whether discrimination has occurred.
Link Prediction in Networks with Core-Fringe Data
However, we find that this is not true; in fact, there is substantial variability in the value of the fringe nodes for prediction.
Simplicity Creates Inequity: Implications for Fairness, Stereotypes, and Interpretability
Thus, simplicity transforms disadvantage into bias against the disadvantaged group.
How Do Classifiers Induce Agents To Invest Effort Strategically?
Algorithms are often used to produce decision-making rules that classify or evaluate individuals.
Direct Uncertainty Prediction for Medical Second Opinions
Our central methodological finding is that Direct Uncertainty Prediction (DUP), training a model to predict an uncertainty score directly from the raw patient features, works better than Uncertainty Via Classification, the two-step process of training a classifier and postprocessing the output distribution to give an uncertainty score.
Found Graph Data and Planted Vertex Covers
A typical way in which network data is recorded is to measure all the interactions among a specified set of core nodes; this produces a graph containing this core together with a potentially larger set of fringe nodes that have links to the core.
Simplicial Closure and higher-order link prediction
Networks provide a powerful formalism for modeling complex systems by using a model of pairwise interactions.
Opinion Dynamics with Varying Susceptibility to Persuasion
This body of literature suggests an interesting perspective on theoretical models of opinion formation by interacting parties in a network: in addition to considering interventions that directly modify people's intrinsic opinions, it is also natural to consider interventions that modify people's susceptibility to persuasion.
Selection Problems in the Presence of Implicit Bias
Over the past two decades, the notion of implicit bias has come to serve as an important component in our understanding of discrimination in activities such as hiring, promotion, and school admissions.
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization.
On Fairness and Calibration
The machine learning community has become increasingly concerned with the potential for bias and discrimination in predictive models.
The Theory is Predictive, but is it Complete? An Application to Human Perception of Randomness
Overall, our results indicate that (i) there is a significant amount of structure in this problem that existing models have yet to capture and (ii) there are rich domains in which machine learning may provide a viable approach to testing completeness.
Comparison-Based Choices
In this work we study comparison-based choice functions, a simple but surprisingly rich class of functions capable of exhibiting so-called choice-set effects.
Survey of Expressivity in Deep Neural Networks
This quantity grows exponentially in the depth of the network, and is responsible for the depth sensitivity observed.
Fair Division via Social Comparison
A general result is that for any two distinct graphs on the same set of nodes and an allocation, there exists a set of valuation functions such that the allocation is locally proportional on one but not the other.
Inherent Trade-Offs in the Fair Determination of Risk Scores
Recent discussion in the public sphere about algorithmic classification has involved tension between competing notions of what it means for a probabilistic classification to be fair to different groups.
On the Expressive Power of Deep Neural Networks
We propose a new approach to the problem of neural network expressivity, which seeks to characterize how structural properties of a neural network family affect the functions it is able to compute.
Assessing Human Error Against a Benchmark of Perfection
An increasing number of domains are providing us with detailed trace data on human decisions in settings where we can evaluate the quality of these decisions via an algorithm.
Do Cascades Recur?
In this paper, we perform a large-scale analysis of cascades on Facebook over significantly longer time scales, and find that a more complex picture emerges, in which many large cascades recur, exhibiting multiple bursts of popularity with periods of quiescence in between.
Can Cascades be Predicted?
On a large sample of photo reshare cascades on Facebook, we find strong performance in predicting whether a cascade will continue to grow in the future.
Engaging with Massive Online Courses
We also report on a large-scale deployment of badges as incentives for engagement in a MOOC, including randomized experiments in which the presentation of badges was varied across sub-populations.
You had me at hello: How phrasing affects memorability
Understanding the ways in which information achieves widespread public awareness is a research question of significant interest.
