Publications & Preprints

(2022). Transformers Learn Shortcuts to Automata.

PDF Cite

(2022). Recurrent Convolutional Neural Networks Learn Succinct Learning Algorithms. NeurIPS 2022.

PDF Cite

(2022). Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit. NeurIPS 2022.

PDF Cite

(2022). Understanding Contrastive Learning Requires Incorporating Inductive Biases. ICML 2022.

PDF Cite

(2022). Inductive Biases and Variable Creation in Self-Attention Mechanisms. ICML 2022.

PDF Cite

(2022). Anti-Concentrated Confidence Bonuses for Scalable Exploration. ICLR 2022.

PDF Cite

(2022). Investigating the Role of Negatives in Contrastive Representation Learning. AISTATS 2022.

PDF Cite

(2021). Gone Fishing: Neural Active Learning with Fisher Embeddings. NeurIPS 2021.

PDF Cite

(2021). Statistical Estimation from Dependent Data. ICML 2021.

PDF Cite

(2021). Acceleration via Fractal Learning Rate Schedules. ICML 2021.

PDF Cite

(2021). Tight Hardness Results for Training Depth-2 ReLU Networks. ITCS 2021.

PDF Cite

(2020). Statistical-Query Lower Bounds via Functional Gradients. NeurIPS 2020.

PDF Cite

(2020). From Boltzmann Machines to Neural Networks and Back Again. NeurIPS 2020.

PDF Cite

(2020). Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent. ICML 2020.

PDF Cite

(2020). Learning Mixtures of Graphs from Epidemic Cascades. ICML 2020.

PDF Cite

(2020). Efficiently Learning Adversarially Robust Halfspaces with Noise. ICML 2020.

PDF Cite

(2020). Approximation Schemes for ReLU Regression. COLT 2020.

PDF Cite

(2019). Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals. NeurIPS 2019 [Spotlight].

PDF Cite

(2019). Learning Ising Models with Independent Failures. COLT 2019.

PDF Cite

(2019). Quantifying Perceptual Distortion of Adversarial Examples.

PDF Cite

(2018). Learning One Convolutional Layer with Overlapping Patches. ICML 2018 [Long Talk].

PDF Cite

(2017). Reliably Learning the ReLU in Polynomial Time. COLT 2017.

PDF Cite