Search Results for author: Jacob Steinhardt

Found 81 papers, 48 papers with code

Statistical Bias in Dataset Replication

no code implementations ICML 2020 Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry

Dataset replication is a useful tool for assessing whether models have overfit to a specific validation set or the exact circumstances under which it was generated.

Adversaries Can Misuse Combinations of Safe Models

no code implementations20 Jun 2024 Erik Jones, Anca Dragan, Jacob Steinhardt

In this work, we show that individually testing models for misuse is inadequate; adversaries can misuse combinations of models even when each individual model is safe.

Interpreting the Second-Order Effects of Neurons in CLIP

no code implementations6 Jun 2024 Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt

We interpret the function of individual neurons in CLIP by automatically describing them using text.

Attribute Zero Shot Segmentation

Approaching Human-Level Forecasting with Language Models

no code implementations28 Feb 2024 Danny Halawi, Fred Zhang, Chen Yueh-Han, Jacob Steinhardt

In this work, we study whether language models (LMs) can forecast at the level of competitive human forecasters.

Decision Making Retrieval

Feedback Loops With Language Models Drive In-Context Reward Hacking

1 code implementation9 Feb 2024 Alexander Pan, Erik Jones, Meena Jagadeesan, Jacob Steinhardt

Language models influence the external world: they query APIs that read and write to web pages, generate content that shapes human behavior, and run system commands as autonomous agents.

Describing Differences in Image Sets with Natural Language

1 code implementation CVPR 2024 Lisa Dunlap, Yuhui Zhang, Xiaohan Wang, Ruiqi Zhong, Trevor Darrell, Jacob Steinhardt, Joseph E. Gonzalez, Serena Yeung-Levy

To aid in this discovery process, we explore the task of automatically describing the differences between two $\textbf{sets}$ of images, which we term Set Difference Captioning.

Language Modelling

How do Language Models Bind Entities in Context?

1 code implementation26 Oct 2023 Jiahai Feng, Jacob Steinhardt

To correctly use in-context information, language models (LMs) must bind entities to their attributes.

Interpreting CLIP's Image Representation via Text-Based Decomposition

1 code implementation9 Oct 2023 Yossi Gandelsman, Alexei A. Efros, Jacob Steinhardt

We decompose the image representation as a sum across individual image patches, model layers, and attention heads, and use CLIP's text representation to interpret the summands.

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

1 code implementation18 Jul 2023 Danny Halawi, Jean-Stanislas Denain, Jacob Steinhardt

The first phenomenon, overthinking, appears when we decode predictions from intermediate layers, given correct vs. incorrect few-shot demonstrations.

Few-Shot Learning

Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations

no code implementations17 Jul 2023 Yanda Chen, Ruiqi Zhong, Narutatsu Ri, Chen Zhao, He He, Jacob Steinhardt, Zhou Yu, Kathleen McKeown

To answer these questions, we propose to evaluate $\textbf{counterfactual simulatability}$ of natural language explanations: whether an explanation can enable humans to precisely infer the model's outputs on diverse counterfactuals of the explained input.


Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations

no code implementations29 Jun 2023 Yongyi Yang, Jacob Steinhardt, Wei Hu

This appears to suggest that the last-layer representations are completely determined by the labels, and do not depend on the intrinsic structure of input distribution.

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition

1 code implementation NeurIPS 2023 Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt, Nika Haghtalab

As the scale of machine learning models increases, trends such as scaling laws anticipate consistent downstream improvements in predictive accuracy.

Mass-Producing Failures of Multimodal Systems with Language Models

1 code implementation NeurIPS 2023 Shengbang Tong, Erik Jones, Jacob Steinhardt

Because CLIP is the backbone for most state-of-the-art multimodal systems, these inputs produce failures in Midjourney 5. 1, DALL-E, VideoFusion, and others.

Language Modelling Self-Driving Cars

Incentivizing High-Quality Content in Online Recommender Systems

no code implementations13 Jun 2023 Xinyan Hu, Meena Jagadeesan, Michael I. Jordan, Jacob Steinhardt

In content recommender systems such as TikTok and YouTube, the platform's recommendation algorithm shapes content producer incentives.

Recommendation Systems

Eliciting Latent Predictions from Transformers with the Tuned Lens

2 code implementations14 Mar 2023 Nora Belrose, Zach Furman, Logan Smith, Danny Halawi, Igor Ostrovsky, Lev McKinney, Stella Biderman, Jacob Steinhardt

We analyze transformers from the perspective of iterative inference, seeking to understand how model predictions are refined layer by layer.

Language Modelling

Automatically Auditing Large Language Models via Discrete Optimization

1 code implementation8 Mar 2023 Erik Jones, Anca Dragan, aditi raghunathan, Jacob Steinhardt

Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging.

Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws

no code implementations23 Feb 2023 Kush Bhatia, Wenshuo Guo, Jacob Steinhardt

We specifically show that the well-studied problem of Gaussian process (GP) bandit optimization is a special case of our framework, and that our bounds either improve or are competitive with known regret guarantees for the Mat\'ern kernel.

Progress measures for grokking via mechanistic interpretability

1 code implementation12 Jan 2023 Neel Nanda, Lawrence Chan, Tom Lieberum, Jess Smith, Jacob Steinhardt

Based on this understanding, we define progress measures that allow us to study the dynamics of training and split training into three continuous phases: memorization, circuit formation, and cleanup.


Discovering Latent Knowledge in Language Models Without Supervision

1 code implementation7 Dec 2022 Collin Burns, Haotian Ye, Dan Klein, Jacob Steinhardt

Existing techniques for training language models can be misaligned with the truth: if we train models with imitation learning, they may reproduce errors that humans make; if we train them to generate text that humans rate highly, they may output errors that human evaluators can't detect.

Imitation Learning Language Modelling +2

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

2 code implementations1 Nov 2022 Kevin Wang, Alexandre Variengien, Arthur Conmy, Buck Shlegeris, Jacob Steinhardt

Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components.

Language Modelling

How Would The Viewer Feel? Estimating Wellbeing From Video Scenarios

1 code implementation18 Oct 2022 Mantas Mazeika, Eric Tang, Andy Zou, Steven Basart, Jun Shern Chan, Dawn Song, David Forsyth, Jacob Steinhardt, Dan Hendrycks

In experiments, we show how video models that are primarily trained to recognize actions and find contours of objects can be repurposed to understand human preferences and the emotional content of videos.

Video Understanding

Supply-Side Equilibria in Recommender Systems

1 code implementation NeurIPS 2023 Meena Jagadeesan, Nikhil Garg, Jacob Steinhardt

Producers seek to create content that will be shown by the recommendation algorithm, which can impact both the diversity and quality of their content.

Recommendation Systems

More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize

no code implementations11 Mar 2022 Alexander Wei, Wei Hu, Jacob Steinhardt

On the other hand, we find that the classical GCV estimator (Craven and Wahba, 1978) accurately predicts generalization risk even in such overparameterized settings.


Capturing Failures of Large Language Models via Human Cognitive Biases

no code implementations24 Feb 2022 Erik Jones, Jacob Steinhardt

Large language models generate complex, open-ended outputs: instead of outputting a class label they write summaries, generate dialogue, or produce working code.

Code Generation

Predicting Out-of-Distribution Error with the Projection Norm

1 code implementation11 Feb 2022 Yaodong Yu, Zitong Yang, Alexander Wei, Yi Ma, Jacob Steinhardt

Projection Norm first uses model predictions to pseudo-label test samples and then trains a new model on the pseudo-labels.

Pseudo Label text-classification +1

Describing Differences between Text Distributions with Natural Language

1 code implementation28 Jan 2022 Ruiqi Zhong, Charlie Snell, Dan Klein, Jacob Steinhardt

We then re-rank the descriptions by checking how often they hold on a larger set of samples with a learned verifier.

Binary Classification Re-Ranking

The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models

1 code implementation ICLR 2022 Alexander Pan, Kush Bhatia, Jacob Steinhardt

Reward hacking -- where RL agents exploit gaps in misspecified reward functions -- has been widely observed, but not yet systematically studied.

Anomaly Detection

PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures

2 code implementations CVPR 2022 Dan Hendrycks, Andy Zou, Mantas Mazeika, Leonard Tang, Bo Li, Dawn Song, Jacob Steinhardt

In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy.

Adversarial Robustness Anomaly Detection +1

The Effect of Model Size on Worst-Group Generalization

no code implementations8 Dec 2021 Alan Pham, Eunice Chan, Vikranth Srivatsa, Dhruba Ghosh, Yaoqing Yang, Yaodong Yu, Ruiqi Zhong, Joseph E. Gonzalez, Jacob Steinhardt

Overparameterization is shown to result in poor test accuracy on rare subgroups under a variety of settings where subgroup information is known.

Grounding Representation Similarity Through Statistical Testing

no code implementations NeurIPS 2021 Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt

To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel alignment (CKA), and other dissimilarity measures.


What Would Jiminy Cricket Do? Towards Agents That Behave Morally

1 code implementation25 Oct 2021 Dan Hendrycks, Mantas Mazeika, Andy Zou, Sahil Patel, Christine Zhu, Jesus Navarro, Dawn Song, Bo Li, Jacob Steinhardt

When making everyday decisions, people are guided by their conscience, an internal sense of right and wrong.

Improving and Assessing Anomaly Detectors for Large-Scale Settings

no code implementations29 Sep 2021 Dan Hendrycks, Steven Basart, Mantas Mazeika, Andy Zou, Joseph Kwon, Mohammadreza Mostajabi, Jacob Steinhardt

We conduct extensive experiments in these more realistic settings for out-of-distribution detection and find that a surprisingly simple detector based on the maximum logit outperforms prior methods in all the large-scale multi-class, multi-label, and segmentation tasks, establishing a simple new baseline for future work.

Out-of-Distribution Detection Segmentation +1

Unsolved Problems in ML Safety

no code implementations28 Sep 2021 Dan Hendrycks, Nicholas Carlini, John Schulman, Jacob Steinhardt

Machine learning (ML) systems are rapidly increasing in size, are acquiring new capabilities, and are increasingly deployed in high-stakes settings.

Learning Equilibria in Matching Markets from Bandit Feedback

no code implementations NeurIPS 2021 Meena Jagadeesan, Alexander Wei, Yixin Wang, Michael I. Jordan, Jacob Steinhardt

Large-scale, two-sided matching platforms must find market outcomes that align with user preferences while simultaneously learning these preferences from data.

Grounding Representation Similarity with Statistical Testing

3 code implementations3 Aug 2021 Frances Ding, Jean-Stanislas Denain, Jacob Steinhardt

To understand neural network behavior, recent works quantitatively compare different networks' learned representations using canonical correlation analysis (CCA), centered kernel alignment (CKA), and other dissimilarity measures.


Measuring Coding Challenge Competence With APPS

3 code implementations20 May 2021 Dan Hendrycks, Steven Basart, Saurav Kadavath, Mantas Mazeika, Akul Arora, Ethan Guo, Collin Burns, Samir Puranik, Horace He, Dawn Song, Jacob Steinhardt

Recent models such as GPT-Neo can pass approximately 20% of the test cases of introductory problems, so we find that machine learning models are now beginning to learn how to code.

BIG-bench Machine Learning Code Generation

Are Larger Pretrained Language Models Uniformly Better? Comparing Performance at the Instance Level

1 code implementation Findings (ACL) 2021 Ruiqi Zhong, Dhruba Ghosh, Dan Klein, Jacob Steinhardt

We develop statistically rigorous methods to address this, and after accounting for pretraining and finetuning noise, we find that our BERT-Large is worse than BERT-Mini on at least 1-4% of instances across MNLI, SST-2, and QQP, compared to the overall accuracy improvement of 2-10%.


Agnostic learning with unknown utilities

no code implementations17 Apr 2021 Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, Jacob Steinhardt

This raises an interesting question whether learning is even possible in our setup, given that obtaining a generalizable estimate of utility $u^*$ might not be possible from finitely many samples.

Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition

1 code implementation17 Mar 2021 Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma

To investigate this gap, we decompose the test risk into its bias and variance components and study their behavior as a function of adversarial training perturbation radii ($\varepsilon$).

Approximating How Single Head Attention Learns

1 code implementation13 Mar 2021 Charlie Snell, Ruiqi Zhong, Dan Klein, Jacob Steinhardt

Our approximation explains why models sometimes attend to salient words, and inspires a toy example where a multi-head attention model can overcome the above hard training distribution by improving learning dynamics rather than expressiveness.

Limitations of Post-Hoc Feature Alignment for Robustness

1 code implementation CVPR 2021 Collin Burns, Jacob Steinhardt

Feature alignment is an approach to improving robustness to distribution shift that matches the distribution of feature activations between the training distribution and test distribution.

Unsupervised Domain Adaptation

Measuring Mathematical Problem Solving With the MATH Dataset

4 code implementations5 Mar 2021 Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, Jacob Steinhardt

To facilitate future research and increase accuracy on MATH, we also contribute a large auxiliary pretraining dataset which helps teach models the fundamentals of mathematics.

Math Math Word Problem Solving +1

How Multipurpose Are Language Models?

no code implementations ICLR 2021 Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt

By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.

Elementary Mathematics World Knowledge

A Rigorous Evaluation of Real-World Distribution Shifts

no code implementations1 Jan 2021 Dan Hendrycks, Steven Basart, Norman Mu, Saurav Kadavath, Frank Wang, Evan Dorundo, Rahul Desai, Tyler Zhu, Samyak Parajuli, Mike Guo, Dawn Song, Jacob Steinhardt, Justin Gilmer

Motivated by this, we introduce a new data augmentation method which advances the state-of-the-art and outperforms models pretrained with 1000x more labeled data.

Data Augmentation

Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming

2 code implementations NeurIPS 2020 Sumanth Dathathri, Krishnamurthy Dvijotham, Alexey Kurakin, aditi raghunathan, Jonathan Uesato, Rudy Bunel, Shreya Shankar, Jacob Steinhardt, Ian Goodfellow, Percy Liang, Pushmeet Kohli

In this work, we propose a first-order dual SDP algorithm that (1) requires memory only linear in the total number of network activations, (2) only requires a fixed number of forward/backward passes through the network per iteration.


Measuring Massive Multitask Language Understanding

13 code implementations7 Sep 2020 Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, Jacob Steinhardt

By comprehensively evaluating the breadth and depth of a model's academic and professional understanding, our test can be used to analyze models across many tasks and to identify important shortcomings.

Elementary Mathematics Multi-task Language Understanding +1

Understanding Attention Training via Output Relevance

no code implementations16 Aug 2020 Charlie Snell, Ruiqi Zhong, Jacob Steinhardt, Dan Klein

If we ablate attention by fixing it to uniform, the output relevance still correlates with the attention of a normally trained model; but if we instead ablate output relevance, attention cannot be learned.


Robust estimation via generalized quasi-gradients

no code implementations28 May 2020 Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

We study the loss landscape of these robust estimation problems, and identify the existence of "generalized quasi-gradients".


Identifying Statistical Bias in Dataset Replication

1 code implementation19 May 2020 Logan Engstrom, Andrew Ilyas, Shibani Santurkar, Dimitris Tsipras, Jacob Steinhardt, Aleksander Madry

We study ImageNet-v2, a replication of the ImageNet dataset on which models exhibit a significant (11-14%) drop in accuracy, even after controlling for a standard human-in-the-loop measure of data quality.

Rethinking Bias-Variance Trade-off for Generalization of Neural Networks

1 code implementation ICML 2020 Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma

We provide a simple explanation for this by measuring the bias and variance of neural networks: while the bias is monotonically decreasing as in the classical theory, the variance is unimodal or bell-shaped: it increases then decreases with the width of the network.

When does the Tukey median work?

no code implementations21 Jan 2020 Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

We show that under TV corruptions, the breakdown point reduces to 1/4 for the same set of distributions.

Scaling Out-of-Distribution Detection for Real-World Settings

3 code implementations25 Nov 2019 Dan Hendrycks, Steven Basart, Mantas Mazeika, Andy Zou, Joe Kwon, Mohammadreza Mostajabi, Jacob Steinhardt, Dawn Song

We conduct extensive experiments in these more realistic settings for out-of-distribution detection and find that a surprisingly simple detector based on the maximum logit outperforms prior methods in all the large-scale multi-class, multi-label, and segmentation tasks, establishing a simple new baseline for future work.

Out-of-Distribution Detection Segmentation +2

Generalized Resilience and Robust Statistics

no code implementations19 Sep 2019 Banghua Zhu, Jiantao Jiao, Jacob Steinhardt

This generalizes a property called resilience previously employed in the special case of mean estimation with outliers.

Testing Robustness Against Unforeseen Adversaries

3 code implementations21 Aug 2019 Max Kaufmann, Daniel Kang, Yi Sun, Steven Basart, Xuwang Yin, Mantas Mazeika, Akul Arora, Adam Dziedzic, Franziska Boenisch, Tom Brown, Jacob Steinhardt, Dan Hendrycks

To narrow in on this discrepancy between research and reality we introduce ImageNet-UA, a framework for evaluating model robustness against a range of unforeseen adversaries, including eighteen new non-L_p attacks.

Adversarial Defense Adversarial Robustness

Natural Adversarial Examples

3 code implementations CVPR 2021 Dan Hendrycks, Kevin Zhao, Steven Basart, Jacob Steinhardt, Dawn Song

We also curate an adversarial out-of-distribution detection dataset called ImageNet-O, which is the first out-of-distribution detection dataset created for ImageNet models.

Adversarial Attack Data Augmentation +2

Transfer of Adversarial Robustness Between Perturbation Types

no code implementations3 May 2019 Daniel Kang, Yi Sun, Tom Brown, Dan Hendrycks, Jacob Steinhardt

We study the transfer of adversarial robustness of deep neural networks between different perturbation types.

Adversarial Robustness

FrAngel: Component-Based Synthesis with Control Structures

2 code implementations13 Nov 2018 Kensen Shi, Jacob Steinhardt, Percy Liang

We present FrAngel, a new approach to component-based synthesis that can synthesize short Java functions with control structures when given a desired signature, a set of input-output examples, and a collection of libraries (without formal specifications).

Programming Languages

Stronger Data Poisoning Attacks Break Data Sanitization Defenses

2 code implementations2 Nov 2018 Pang Wei Koh, Jacob Steinhardt, Percy Liang

In this paper, we develop three attacks that can bypass a broad range of common data sanitization defenses, including anomaly detectors based on nearest neighbors, training loss, and singular-value decomposition.

Data Poisoning Sentiment Analysis +2

Semidefinite relaxations for certifying robustness to adversarial examples

3 code implementations NeurIPS 2018 Aditi Raghunathan, Jacob Steinhardt, Percy Liang

One promise of ending the arms race is developing certified defenses, ones which are provably robust against all attackers in some family.

Troubling Trends in Machine Learning Scholarship

no code implementations9 Jul 2018 Zachary C. Lipton, Jacob Steinhardt

Collectively, machine learning (ML) researchers are engaged in the creation and dissemination of knowledge about data-driven algorithms.

BIG-bench Machine Learning

Sever: A Robust Meta-Algorithm for Stochastic Optimization

1 code implementation7 Mar 2018 Ilias Diakonikolas, Gautam Kamath, Daniel M. Kane, Jerry Li, Jacob Steinhardt, Alistair Stewart

In high dimensions, most machine learning methods are brittle to even a small fraction of structured outliers.

Stochastic Optimization

Certified Defenses against Adversarial Examples

4 code implementations ICLR 2018 Aditi Raghunathan, Jacob Steinhardt, Percy Liang

While neural networks have achieved high accuracy on standard image classification benchmarks, their accuracy drops to nearly zero in the presence of small adversarial perturbations to test inputs.

Adversarial Attack Adversarial Defense +1

Better Agnostic Clustering Via Relaxed Tensor Norms

no code implementations20 Nov 2017 Pravesh K. Kothari, Jacob Steinhardt

As an immediate corollary, for any $\gamma > 0$, we obtain an efficient algorithm for learning the means of a mixture of $k$ arbitrary \Poincare distributions in $\mathbb{R}^d$ in time $d^{O(1/\gamma)}$ so long as the means have separation $\Omega(k^{\gamma})$.


Certified Defenses for Data Poisoning Attacks

2 code implementations NeurIPS 2017 Jacob Steinhardt, Pang Wei Koh, Percy Liang

Machine learning systems trained on user-provided data are susceptible to data poisoning attacks, whereby malicious users inject false training data with the aim of corrupting the learned model.

Data Poisoning

Does robustness imply tractability? A lower bound for planted clique in the semi-random model

no code implementations17 Apr 2017 Jacob Steinhardt

This matches the conjectured computational threshold for the classical planted clique problem, and thus raises the intriguing possibility that, once we require robustness, there is no computational-statistical gap for planted clique.

Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers

no code implementations15 Mar 2017 Jacob Steinhardt, Moses Charikar, Gregory Valiant

We introduce a criterion, resilience, which allows properties of a dataset (such as its mean or best low rank approximation) to be robustly computed, even in the presence of a large fraction of arbitrary additional data.

Learning from Untrusted Data

no code implementations7 Nov 2016 Moses Charikar, Jacob Steinhardt, Gregory Valiant

For example, given a dataset of $n$ points for which an unknown subset of $\alpha n$ points are drawn from a distribution of interest, and no assumptions are made about the remaining $(1-\alpha)n$ points, is it possible to return a list of $\operatorname{poly}(1/\alpha)$ answers, one of which is correct?

Stochastic Optimization

Concrete Problems in AI Safety

1 code implementation21 Jun 2016 Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, Dan Mané

Rapid progress in machine learning and artificial intelligence (AI) has brought increasing attention to the potential impacts of AI technologies on society.

BIG-bench Machine Learning Safe Exploration

Unsupervised Risk Estimation Using Only Conditional Independence Structure

no code implementations NeurIPS 2016 Jacob Steinhardt, Percy Liang

We show how to estimate a model's test error from unlabeled data, on distributions very different from the training distribution, while assuming only that certain conditional independencies are preserved between train and test.

Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction

no code implementations NeurIPS 2016 Jacob Steinhardt, Gregory Valiant, Moses Charikar

We consider a crowdsourcing model in which $n$ workers are asked to rate the quality of $n$ items previously generated by other workers.

Learning with Relaxed Supervision

1 code implementation NeurIPS 2015 Jacob Steinhardt, Percy S. Liang

For weakly-supervised problems with deterministic constraints between the latent variables and observed output, learning necessitates performing inference over latent variables conditioned on the output, which can be intractable no matter how simple the model family is.


Learning Where to Sample in Structured Prediction

1 code implementation9 May 2015 Tianlin Shi, Jacob Steinhardt, Percy Liang

In structured prediction, most inference algorithms allocate a homogeneous amount of computation to all parts of the output, which can be wasteful when different parts vary widely in terms of difficulty.

Reinforcement Learning (RL) Structured Prediction

Learning Fast-Mixing Models for Structured Prediction

1 code implementation24 Feb 2015 Jacob Steinhardt, Percy Liang

Markov Chain Monte Carlo (MCMC) algorithms are often used for approximate inference inside learning, but their slow mixing can be difficult to diagnose and the approximations can seriously degrade learning.

Structured Prediction

Reified Context Models

1 code implementation24 Feb 2015 Jacob Steinhardt, Percy Liang

A classic tension exists between exact inference in a simple model and approximate inference in a complex model.

The Statistics of Streaming Sparse Regression

no code implementations13 Dec 2014 Jacob Steinhardt, Stefan Wager, Percy Liang

We present a sparse analogue to stochastic gradient descent that is guaranteed to perform well under similar conditions to the lasso.


Cannot find the paper you are looking for? You can Submit a new open access paper.