Search Results for author:
Found 132 papers, 82 papers with code
Diffusing Differentiable Representations
We introduce a novel, training-free method for sampling differentiable representations (diffreps) using pretrained diffusion models.
Blind Inverse Problem Solving Made Easy by Text-to-Image Latent Diffusion
Blind inverse problems, where both the target data and forward operator are unknown, are crucial to many computer vision applications.
Inference Optimal VLMs Need Only One Visual Token but Larger Models
Our results reveal a surprising trend: for visual reasoning tasks, the inference-optimal behavior in VLMs, i. e., minimum downstream error at any given fixed inference compute, is achieved when using the largest LLM that fits within the inference budget while minimizing visual token count - often to a single token.
One-Step Diffusion Distillation through Score Implicit Matching
In this paper, we present Score Implicit Matching (SIM) a new approach to distilling pre-trained diffusion models into single-step generator models, while maintaining almost the same sample generation ability as the original model as well as being data-free with no need of training samples for distillation.
Rethinking Distance Metrics for Counterfactual Explainability
Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning.
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws
The composition of pretraining data is a key determinant of foundation models' performance, but there is no standard guideline for allocating a limited computational budget across different data sources.
Mimetic Initialization Helps State Space Models Learn to Recall
Recent work has shown that state space models such as Mamba are significantly worse than Transformers on recall-based tasks due to the fact that their state size is constant with respect to their input sequence length.
Context-Parametric Inversion: Why Instruction Finetuning May Not Actually Improve Context Reliance
However, models struggle to reliably follow the input context, especially when it conflicts with their parametric knowledge from pretraining.
Finetuning CLIP to Reason about Pairwise Differences
A notable drawback of CLIP, however, is that the resulting embedding space seems to lack some of the structure of their purely text-based alternatives.
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
In this work, we present a method that is able to distill a pretrained Transformer architecture into alternative architectures such as state space models (SSMs).
Prompt Recovery for Image Generation Models: A Comparative Study of Discrete Optimizers
Recovering natural language prompts for image generation models, solely based on the generated images is a difficult discrete optimization problem.
FUSE-ing Language Models: Zero-Shot Adapter Discovery for Prompt Optimization Across Tokenizers
The widespread use of large language models has resulted in a multitude of tokenizers and embedding spaces, making knowledge transfer in prompt discovery tasks difficult.
Consistency Models Made Easy
For example, as of 2024, training a state-of-the-art CM on CIFAR-10 takes one week on 8 GPUs.
Ranked #11 on
Image Generation
on ImageNet 64x64
Understanding Hallucinations in Diffusion Models through Mode Interpolation
Specifically, we find that diffusion models smoothly "interpolate" between nearby data modes in the training set, to generate samples that are completely outside the support of the original training distribution; this phenomenon leads diffusion models to generate artifacts that never existed in real data (i. e., hallucinations).
Rethinking LLM Memorization through the Lens of Adversarial Compression
The ACR overcomes the limitations of existing notions of memorization by (i) offering an adversarial view of measuring memorization, especially for monitoring unlearning and compliance; and (ii) allowing for the flexibility to measure memorization for arbitrary strings at a reasonably low compute.
Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic
Vision-language models (VLMs) are trained for thousands of GPU hours on carefully curated web datasets.
Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Prompt engineering is effective for controlling the output of text-to-image (T2I) generative models, but it is also laborious due to the need for manually crafted prompts.
AcceleratedLiNGAM: Learning Causal DAGs at the speed of GPUs
Existing causal discovery methods based on combinatorial optimization or search are slow, prohibiting their application on large-scale datasets.
Massive Activations in Large Language Models
We observe an empirical phenomenon in Large Language Models (LLMs) -- very few activations exhibit significantly larger values than others (e. g., 100, 000 times larger).
Bayesian Neural Networks with Domain Knowledge Priors
Bayesian neural networks (BNNs) have recently gained popularity due to their ability to quantify model uncertainty.
An Axiomatic Approach to Model-Agnostic Concept Explanations
Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model.
TOFU: A Task of Fictitious Unlearning for LLMs
Large language models trained on massive corpora of data from the web can memorize and reproduce sensitive or private data raising both legal and ethical concerns.
Scaling Laws for Data Filtering-- Data Curation cannot be Compute Agnostic
Our work bridges this important gap in the literature by developing scaling laws that characterize the differing utility of various data subsets and accounting for how this diminishes for a data point at its nth repetition.
One-Step Diffusion Distillation via Deep Equilibrium Models
We demonstrate that the DEQ architecture is crucial to this capability, as GET matches a $5\times$ larger ViT in terms of FID scores while striking a critical balance of computational cost and image quality.
Deep Equilibrium Based Neural Operators for Steady-State PDEs
Motivated by this observation, we propose FNO-DEQ, a deep equilibrium variant of the FNO architecture that directly solves for the solution of a steady-state PDE as the infinite-depth fixed point of an implicit operator layer using a black-box root solver and differentiates analytically through this fixed point resulting in $\mathcal{O}(1)$ training memory.
Manifold Preserving Guided Diffusion
Despite the recent advancements, conditional image generation still faces challenges of cost, generalizability, and the need for task-specific training.
Projected Off-Policy Q-Learning (POP-QL) for Stabilizing Offline Reinforcement Learning
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy.
TorchDEQ: A Library for Deep Equilibrium Models
Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to fixed points of neural networks, are of growing interest in the deep learning community.
On the Neural Tangent Kernel of Equilibrium Models
This work studies the neural tangent kernel (NTK) of the deep equilibrium (DEQ) model, a practical ``infinite-depth'' architecture which directly computes the infinite-depth limit of a weight-tied network via root-finding.
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
To analyze this, we revisit the theoretical conditions from Miller et al. (2021) that outline the types of distribution shifts needed for perfect ACL in linear models.
Understanding prompt engineering may not require rethinking generalization
Zero-shot learning in prompted vision-language models, the practice of crafting prompts to build classifiers without an explicit training process, has achieved impressive performance in many settings.
Representation Engineering: A Top-Down Approach to AI Transparency
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience.
Ranked #3 on
Question Answering
on TruthfulQA
Universal and Transferable Adversarial Attacks on Aligned Language Models
Specifically, our approach finds a suffix that, when attached to a wide range of queries for an LLM to produce objectionable content, aims to maximize the probability that the model produces an affirmative response (rather than refusing to answer).
Can Neural Network Memorization Be Localized?
Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks $\textit{memorize}$ "hard" examples in the final few layers of the model.
Monotone deep Boltzmann machines
Deep Boltzmann machines (DBMs), one of the first ``deep'' learning methods ever studied, are multi-layered probabilistic models governed by a pairwise energy function that describes the likelihood of all variables/nodes in the network.
Text Descriptions are Compressive and Invariant Representations for Visual Learning
This method first automatically generates multiple visual descriptions of each class via a large language model (LLM), then uses a VLM to translate these descriptions to a set of visual feature embeddings of each image, and finally uses sparse logistic regression to select a relevant subset of these features to classify each image.
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
However, naively removing all such data could also be wasteful, as it throws away images that contain visual features (in addition to overlapping text).
Localized Text-to-Image Generation for Free via Cross Attention Control
Despite the tremendous success in text-to-image generative models, localized text-to-image generation (that is, generating objects or features at specific locations in an image while maintaining a consistent overall generation) still requires either explicit training or substantial additional inference time.
A Simple and Effective Pruning Approach for Large Language Models
Motivated by the recent observation of emergent large magnitude features in LLMs, our approach prunes weights with the smallest magnitudes multiplied by the corresponding input activations, on a per-output basis.
On the Joint Interaction of Models, Data, and Features
Thus, we believe this work provides valuable new insight into our understanding of feature learning.
Mimetic Initialization of Self-Attention Layers
It is notoriously difficult to train Transformers on small datasets; typically, large pre-trained models are instead used as the starting point.
The Update-Equivalence Framework for Decision-Time Planning
Using this framework, we derive a provably sound search algorithm for fully cooperative games based on mirror descent and a search algorithm for adversarial games based on magnetic mirror descent.
Learning with Explanation Constraints
In this paper, we formalize this notion as learning from explanation constraints and provide a learning theoretic framework to analyze how such explanations can improve the learning of our models.
Sinkhorn-Flow: Predicting Probability Mass Flow in Dynamical Systems Using Optimal Transport
Predicting how distributions over discrete variables vary over time is a common task in time series forecasting.
Model-tuning Via Prompts Makes NLP Models Adversarially Robust
Across 5 NLP datasets, 4 adversarial attacks, and 3 different models, MVP improves performance against adversarial substitutions by an average of 8% over standard methods and even outperforms adversarial training-based state-of-art defenses by 3. 5%.
Single Image Backdoor Inversion via Robust Smoothed Classifiers
Insipired by recent advances in adversarial robustness, our method SmoothInv starts from a single clean image, and then performs projected gradient descent towards the target class on a robust smoothed version of the original backdoored classifier.
Permutation Equivariant Neural Functionals
The key building blocks of this framework are NF-Layers (neural functional layers) that we constrain to be permutation equivariant through an appropriate parameter sharing scheme.
Abstracting Imperfect Information Away from Two-Player Zero-Sum Games
Because these regularized equilibria can be made arbitrarily close to Nash equilibria, our result opens the door to a new perspective to solving two-player zero-sum games and yields a simplified framework for decision-time planning in two-player zero-sum games, void of the unappealing properties that plague existing decision-time planning approaches.
Function Approximation for Solving Stackelberg Equilibrium in Large Perfect Information Games
Function approximation (FA) has been a critical component in solving large zero-sum games.
Losses over Labels: Weakly Supervised Learning via Direct Loss Construction
Owing to the prohibitive costs of generating large amounts of labeled data, programmatic weak supervision is a growing paradigm within machine learning.
Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth
Neural networks with sinusoidal activations have been proposed as an alternative to networks with traditional activation functions.
Characterizing Datapoints via Second-Split Forgetting
Popular metrics derived from these dynamics include (i) the epoch at which examples are first correctly classified; (ii) the number of times their predictions flip during training; and (iii) whether their prediction flips if they are held out.
Perfectly Secure Steganography Using Minimum Entropy Coupling
Steganography is the practice of encoding secret information into innocuous content in such a manner that an adversarial third party would not realize that there is hidden meaning.
Understanding the Covariance Structure of Convolutional Filters
In this work, we first observe that such learned filters have highly-structured covariance matrices, and moreover, we find that covariances calculated from small networks may be used to effectively initialize a variety of larger networks of different depths, widths, patch sizes, and kernel sizes, indicating a degree of model-independence to the covariance structure.
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods.
(Certified!!) Adversarial Robustness for Free!
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models.
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm.
Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Randomized smoothing (RS) has been shown to be a fast, scalable technique for certifying the robustness of deep neural network classifiers.
Deep Equilibrium Optical Flow Estimation
Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update operations to emulate traditional algorithms by encouraging iterative refinements toward a stable flow estimation.
Ranked #1 on
Optical Flow Estimation
on KITTI 2015 (train)
Patches Are All You Need?
Despite its simplicity, we show that the ConvMixer outperforms the ViT, MLP-Mixer, and some of their variants for similar parameter counts and data set sizes, in addition to outperforming classical vision models such as the ResNet.
Ranked #100 on
Image Classification
on CIFAR-10
Monte Carlo Tree Search With Iteratively Refining State Abstractions
In this work, we present a method, called abstraction refining, for extending MCTS to stochastic environments which, unlike progressive widening, leverages the geometry of the state space.
Robustness between the worst and average case
Several recent works in machine learning have focused on evaluating the test-time robustness of a classifier: how well the classifier performs not just on the target domain it was trained upon, but upon perturbed examples.
$(\textrm{Implicit})^2$: Implicit Layers for Implicit Representations
Recent research in deep learning has investigated two very different forms of ''implicitness'': implicit representations model high-frequency data such as images or 3D shapes directly via a low-dimensional neural network (often using e. g., sinusoidal bases or nonlinearities); implicit layers, in contrast, refer to techniques where the forward pass of a network is computed via non-linear dynamical systems, such as fixed-point or differential equation solutions, with the backward pass computed via the implicit function theorem.
Joint inference and input optimization in equilibrium networks
Many tasks in deep learning involve optimizing over the \emph{inputs} to a network to minimize or maximize some objective; examples include optimization over latent spaces in a generative model to match a target image, or adversarially perturbing an input to worsen classifier performance.
Adversarially Robust Learning for Security-Constrained Optimal Power Flow
In recent years, the ML community has seen surges of interest in both adversarially robust learning and implicit layers, but connections between these two areas have seldom been explored.
Communicating via Markov Decision Processes
We contribute a theoretically grounded approach to MCGs based on maximum entropy reinforcement learning and minimum entropy coupling that we call MEME.
Stabilizing Equilibrium Models by Jacobian Regularization
Deep equilibrium networks (DEQs) are a new class of models that eschews traditional depth in favor of finding the fixed point of a single nonlinear layer.
Assessing Generalization of SGD via Disagreement
We empirically show that the test error of deep networks can be estimated by simply training the same architecture on the same training set but with a different run of Stochastic Gradient Descent (SGD), and measuring the disagreement rate between the two networks on unlabeled test data.
DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting
Analyzing the worst-case performance of deep neural networks against input perturbations amounts to solving a large-scale non-convex optimization problem, for which several past works have proposed convex relaxations as a promising alternative.
DORO: Distributional and Outlier Robust Optimization
Many machine learning tasks involve subpopulation shift where the testing data distribution is a subpopulation of the training distribution.
Enforcing Policy Feasibility Constraints through Differentiable Projection for Energy Optimization
Specifically, we incorporate a differentiable projection layer within a neural network-based policy to enforce that all learned actions are feasible.
RATT: Leveraging Unlabeled Data to Guarantee Generalization
To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data.
DC3: A learning method for optimization with hard constraints
Large optimization problems with hard constraints arise in many settings, yet classical solvers are often prohibitively slow, motivating the use of deep networks as cheap "approximate solvers."
Orthogonalizing Convolutional Layers with the Cayley Transform
Recent work has highlighted several advantages of enforcing orthogonality in the weight layers of deep networks, such as maintaining the stability of activations, preserving gradient norms, and enhancing adversarial robustness by enforcing low Lipschitz constants.
Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification
Compared to the typically tightest but very costly semidefinite programming (SDP) based incomplete verifiers, we obtain higher verified accuracy with three orders of magnitudes less verification time.
Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability.
On Proximal Policy Optimization's Heavy-tailed Gradients
In this paper, we present a detailed empirical study to characterize the heavy-tailed nature of the gradients of the PPO surrogate reward function.
Deep Archimedean Copulas
A central problem in machine learning and statistics is to model joint densities of random variables from data.
Efficient semidefinite-programming-based inference for binary and multi-class MRFs
Probabilistic inference in pairwise Markov Random Fields (MRFs), i. e. computing the partition function or computing a MAP estimate of the variables, is a foundational problem in probabilistic graphical models.
Community detection using fast low-cardinality semidefinite programming
Modularity maximization has been a fundamental tool for understanding the community structure of a network, but the underlying optimization problem is nonconvex and NP-hard to solve.
Challenging common interpretability assumptions in feature attribution explanations
As machine learning and algorithmic decision making systems are increasingly being leveraged in high-stakes human-in-the-loop settings, there is a pressing need to understand the rationale of their predictions.
Decision Making
Explainable Artificial Intelligence (XAI)
+1
Enforcing robust control guarantees within neural network policies
When designing controllers for safety-critical systems, practitioners often face a challenging tradeoff between robustness and performance.
Poisoned classifiers are not only backdoored, they are fundamentally broken
Under this threat model, we propose a test-time, human-in-the-loop attack method to generate multiple effective alternative triggers without access to the initial backdoor and the training data.
Gaussian MRF Covariance Modeling for Efficient Black-Box Adversarial Attacks
We study the problem of generating adversarial examples in a black-box setting, where we only have access to a zeroth order oracle, providing us with loss function evaluations.
Learning perturbation sets for robust machine learning
In this paper, we aim to bridge this gap by learning perturbation sets from data, in order to characterize real-world effects for robust training and evaluation.
Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data input.
Combining Differentiable PDE Solvers and Graph Neural Networks for Fluid Flow Prediction
Solving large complex partial differential equations (PDEs), such as those that arise in computational fluid dynamics (CFD), is a computationally expensive process.
Provably Safe PAC-MDP Exploration Using Analogies
A key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration (needed to attain good performance on the task) with safety (needed to avoid catastrophic failure).
Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications
Additionally, we show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges, allowing us to train a virtual sensor for fuel injection which is provably guaranteed to have at most 10. 69% relative error under noise while maintaining 3% relative error on non-adversarial data within normalized fuel injection ranges of 0. 6 to 1. 0.
Monotone operator equilibrium networks
We then develop a parameterization of the network which ensures that all operators remain monotone, which guarantees the existence of a unique equilibrium point.
Multiscale Deep Equilibrium Models
These simultaneously-learned multi-resolution features allow us to train a single model on a diverse set of tasks and loss functions, such as using a single MDEQ to perform both image classification and semantic segmentation.
Ranked #50 on
Semantic Segmentation
on Cityscapes val
Differentiable learning of numerical rules in knowledge graphs
Rules over a knowledge graph (KG) capture interpretable patterns in data and can be used for KG cleaning and completion.
Denoised Smoothing: A Provable Defense for Pretrained Classifiers
We present a method for provably defending any pretrained image classifier against $\ell_p$ adversarial attacks.
Overfitting in adversarially robust deep learning
Based upon this observed effect, we show that the performance gains of virtually all recent algorithmic improvements upon adversarial training can be matched by simply using early stopping.
Certified Robustness to Label-Flipping Attacks via Randomized Smoothing
Machine learning algorithms are known to be susceptible to data poisoning attacks, where an adversary manipulates the training data to degrade performance of the resulting classifier.
Learning Stable Deep Dynamics Models
Deep networks are commonly used to model dynamical systems, predicting how the state of a system will evolve over time (either autonomously or in response to control inputs).
Fast is better than free: Revisiting adversarial training
Furthermore we show that FGSM adversarial training can be further accelerated by using standard techniques for efficient training of deep networks, allowing us to learn a robust CIFAR10 classifier with 45% robust accuracy to PGD attacks with $\epsilon=8/255$ in 6 minutes, and a robust ImageNet classifier with 43% robust accuracy at $\epsilon=2/255$ in 12 hours, in comparison to past work based on "free" adversarial training which took 10 and 50 hours to reach the same respective thresholds.
AP-Perf: Incorporating Generic Performance Metrics in Differentiable Learning
We propose a method that enables practitioners to conveniently incorporate custom non-decomposable performance metrics into differentiable learning pipelines, notably those based upon neural network architectures.
Dynamic Modeling and Equilibria in Fair Decision Making
Recent studies on fairness in automated decision making systems have both investigated the potential future impact of these decisions on the population at large, and emphasized that imposing ''typical'' fairness constraints such as demographic parity or equality of opportunity does not guarantee a benefit to disadvantaged groups.
Adversarial Music: Real World Audio Adversary Against Wake-word Detection System
In this work, we target our attack on the wake-word detection system, jamming the model with some inconspicuous background music to deactivate the VAs while our audio adversary is present.
Black-box Adversarial Attacks with Bayesian Optimization
We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs.
Certified Robustness to Adversarial Label-Flipping Attacks via Randomized Smoothing
This paper considers label-flipping attacks, a type of data poisoning attack where an adversary relabels a small number of examples in a training set in order to degrade the performance of the resulting classifier.
Adversarial Robustness Against the Union of Multiple Perturbation Models
Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers.
Deep Equilibrium Models
We present a new approach to modeling sequential data: the deep equilibrium model (DEQ).
Ranked #29 on
Language Modelling
on Penn Treebank (Word Level)
The Limited Multi-Label Projection Layer
We propose the Limited Multi-Label (LML) projection layer as a new primitive operation for end-to-end learning systems.
Perceptual Based Adversarial Audio Attacks
Recent work has shown the possibility of adversarial attacks on automatic speechrecognition (ASR) systems.
Audio and Speech Processing Sound
Multimodal Transformer for Unaligned Multimodal Language Sequences
Human language is often multimodal, which comprehends a mixture of natural language, facial gestures, and acoustic behaviors.
Ranked #6 on
Multimodal Sentiment Analysis
on MOSI
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the network is resilient to small random noise added to its parameters.
Adversarial camera stickers: A physical camera-based attack on deep learning systems
In this work, we consider an alternative question: is it possible to fool deep classifiers, over all perceived objects of a certain type, by physically manipulating the camera itself?
Large Scale Learning of Agent Rationality in Two-Player Zero-Sum Games
With the recent advances in solving large, zero-sum extensive form games, there is a growing interest in the inverse problem of inferring underlying game parameters given only access to agent actions.
Wasserstein Adversarial Examples via Projected Sinkhorn Iterations
In this paper, we propose a new threat model for adversarial attacks based on the Wasserstein distance.
Uniform convergence may be unable to explain generalization in deep learning
Aimed at explaining the surprisingly good generalization behavior of overparameterized deep networks, recent works have developed a variety of generalization bounds for deep learning, all based on the fundamental learning-theoretic technique of uniform convergence.
Certified Adversarial Robustness via Randomized Smoothing
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm.
Ranked #3 on
Robust classification
on CIFAR-10
Generalization in Deep Networks: The Role of Distance from Initialization
Why does training deep neural networks using stochastic gradient descent (SGD) result in a generalization error that does not worsen with the number of parameters in the network?
Low-rank semidefinite programming for the MAX2SAT problem
This paper proposes a new algorithm for solving MAX2SAT problems based on combining search methods with semidefinite programming approaches.
End-to-End Differentiable Physics for Learning and Control
We present a differentiable physics engine that can be integrated as a module in deep neural networks for end-to-end learning.
Differentiable MPC for End-to-end Planning and Control
We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces.
A Continuous-Time View of Early Stopping for Least Squares
Our primary focus is to compare the risk of gradient flow to that of ridge regression.
Trellis Networks for Sequence Modeling
On the other hand, we show that truncated recurrent networks are equivalent to trellis networks with special sparsity structure in their weight matrices.
Scaling provable adversarial defenses
Recent work has developed methods for learning deep network classifiers that are provably robust to norm-bounded adversarial perturbation; however, these methods are currently only possible for relatively small feedforward networks.
What game are we playing? End-to-end learning in normal and extensive form games
Although recent work in AI has made great progress in solving large, zero-sum, extensive-form games, the underlying assumption in most past work is that the parameters of the game itself are known to the agents.
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
Our results indicate that a simple convolutional architecture outperforms canonical recurrent networks such as LSTMs across a diverse range of tasks and datasets, while demonstrating longer effective memory.
Ranked #4 on
Music Modeling
on Nottingham
Realtime query completion via deep language models
Search engine users nowadays heavily depend on query completion and correction to shape their queries.
Convolutional Sequence Modeling Revisited
This paper revisits the problem of sequence modeling using convolutional architectures.
Ranked #84 on
Language Modelling
on WikiText-103
Provable defenses against adversarial examples via the convex outer adversarial polytope
We propose a method to learn deep ReLU-based classifiers that are provably robust against norm-bounded adversarial perturbations on the training data.
Gradient descent GAN optimization is locally stable
Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic.
The Mixing method: low-rank coordinate descent for semidefinite programming with diagonal constraints
In this paper, we propose a low-rank coordinate descent approach to structured semidefinite programming with diagonal constraints.
Task-based End-to-end Model Learning in Stochastic Optimization
With the increasing popularity of machine learning techniques, it has become common to see prediction algorithms operating within some larger process.
OptNet: Differentiable Optimization as a Layer in Neural Networks
This paper presents OptNet, a network architecture that integrates optimization problems (here, specifically in the form of quadratic programs) as individual layers in larger end-to-end trainable deep networks.
Input Convex Neural Networks
We show that many existing neural network architectures can be made input-convex with a minor modification, and develop specialized optimization algorithms tailored to this setting.
Probabilistic Segmentation via Total Variation Regularization
We present a convex approach to probabilistic segmentation and modeling of time series data.
Contextually Supervised Source Separation with Application to Energy Disaggregation
We propose a new framework for single-channel source separation that lies between the fully supervised and unsupervised setting.
