[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ skip to main content
10.5555/3524938guideproceedingsBook PagePublication PagesConference Proceedingsacm-pubtype
ICML'20: Proceedings of the 37th International Conference on Machine Learning
2020 Proceeding
Publisher:
  • JMLR.org
Conference:
ICML'20: International Conference on Machine LearningJuly 13 - 18, 2020
Published:
13 July 2020

Reflects downloads up to 11 Dec 2024Bibliometrics
Abstract

No abstract available.

research-article
Free
Selective Dyna-style planning under limited model capacity
Article No.: 1, Pages 1–10

In model-based reinforcement learning, planning with an imperfect model of the environment has the potential to harm learning progress. But even when a model is imperfect, it may still contain information that is useful for planning. In this paper, we ...

research-article
Free
A distributional view on multi-objective policy optimization
Article No.: 2, Pages 11–22

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over objectives in their ...

research-article
Free
Efficient optimistic exploration in linear-quadratic regulators via lagrangian relaxation
Article No.: 3, Pages 23–31

We study the exploration-exploitation dilemma in the linear quadratic regulator (LQR) setting. Inspired by the extended value iteration algorithm used in optimistic algorithms for finite MDPs, we propose to relax the optimistic optimization of OFU-LQ and ...

research-article
Free
Super-efficiency of automatic differentiation for functions defined as a minimum
Article No.: 4, Pages 32–41

In min-min optimization or max-min optimization, one has to compute the gradient of a function defined as a minimum. In most cases, the minimum has no closed-form, and an approximation is obtained via an iterative algorithm. There are two usual ways of ...

research-article
Free
A geometric approach to archetypal analysis via sparse projections
Article No.: 5, Pages 42–51

Archetypal analysis (AA) aims to extract patterns using self-expressive decomposition of data as convex combinations of extremal points (on the convex hull) of the data. This work presents a computationally efficient greedy AA (GAA) algorithm. GAA ...

research-article
Free
Context-aware local differential privacy
Article No.: 6, Pages 52–62

Local differential privacy (LDP) is a strong notion of privacy that often leads to a significant drop in utility. The original definition of LDP assumes that all the elements in the data domain are equally sensitive. However, in many real-life ...

research-article
Free
Efficient intervention design for causal discovery with latents
Article No.: 7, Pages 63–73

We consider recovering a causal graph in presence of latent variables, where we seek to minimize the cost of interventions used in the recovery process. We consider two intervention cost models: (1) a linear cost model where the cost of an intervention on ...

research-article
Free
The neural tangent kernel in high dimensions: triple descent and a multi-scale theory of generalization
Article No.: 8, Pages 74–84

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably well. An ...

research-article
Free
Rank aggregation from pairwise comparisons in the presence of adversarial corruptions
Article No.: 9, Pages 85–95

Rank aggregation from pairwise preferences has widespread applications in recommendation systems and information retrieval. Given the enormous economic and societal impact of these applications, and the consequent incentives for malicious players to ...

research-article
Free
Boosting for control of dynamical systems
Article No.: 10, Pages 96–103

We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak ...

research-article
Free
An optimistic perspective on offline reinforcement learning
Article No.: 11, Pages 104–114

Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN Replay Dataset comprising the entire replay experience of a ...

research-article
Free
Optimal bounds between f-divergences and integral probability metrics
Article No.: 12, Pages 115–124

The families of f-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are commonly used in optimization and estimation. In this work, we systematically study the ...

research-article
Free
LazyIter: a fast algorithm for counting Markov equivalent DAGs and designing experiments
Article No.: 13, Pages 125–133

The causal relationships among a set of random variables are commonly represented by a Directed Acyclic Graph (DAG), where there is a directed edge from variable X to variable Y if X is a direct cause of Y. From the purely observational data, the true ...

research-article
Free
Learning what to defer for maximum independent sets
Article No.: 14, Pages 134–144

Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields. Recently, deep reinforcement learning (DRL) frameworks have gained considerable attention as a new approach: they can automate the design of a ...

research-article
Free
Invariant risk minimization games
Article No.: 15, Pages 145–155

The standard risk minimization paradigm of machine learning is brittle when operating in environments whose test distributions are different from the training distribution due to spurious correlations. Training on data from many environments and finding ...

research-article
Free
Why bigger is not always better: on finite and infinite neural networks
Article No.: 16, Pages 156–164

Recent work has argued that neural networks can be understood theoretically by taking the number of channels to infinity, at which point the outputs become Gaussian process (GP) distributed. However, we note that infinite Bayesian neural networks lack a ...

research-article
Free
Discriminative Jackknife: quantifying uncertainty in deep learning via higher-order influence functions
Article No.: 17, Pages 165–174

Deep learning models achieve high predictive accuracy across a broad spectrum of tasks, but rigorously quantifying their predictive uncertainty remains challenging. Usable estimates of predictive uncertainty should (1) cover the true prediction targets ...

research-article
Free
Frequentist uncertainty in recurrent neural networks via blockwise influence functions
Article No.: 18, Pages 175–190

Recurrent neural networks (RNNs) are instrumental in modelling sequential and time-series data. Yet, when using RNNs to inform decision-making, predictions by themselves are not sufficient--we also need estimates of predictive uncertainty. Existing ...

research-article
Free
Random extrapolation for primal-dual coordinate descent
Article No.: 19, Pages 191–201

We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function. Our method updates only a subset of primal and dual variables with sparse data, ...

research-article
Free
A new regret analysis for Adam-type algorithms
Article No.: 20, Pages 202–210

In this paper, we focus on a theory-practice gap for Adam and its variants (AMSGrad, AdamNC, etc.). In practice, these algorithms are used with a constant first-order moment parameter β1 (typically between 0.9 and 0.99). In theory, regret guarantees for ...

research-article
Free
Restarted Bayesian online change-point detector achieves optimal detection delay
Article No.: 21, Pages 211–221

In this paper, we consider the problem of sequential change-point detection where both the changepoints and the distributions before and after the change are assumed to be unknown. For this problem of primary importance in statistical and sequential ...

research-article
Free
Maximum likelihood with bias-corrected calibration is hard-to-beat at label shift adaptation
Article No.: 22, Pages 222–232

Label shift refers to the phenomenon where the prior class probability p(y) changes between the training and test distributions, while the conditional probability p(x|y) stays fixed. Label shift arises in settings like medical diagnosis, where a ...

research-article
Free
The implicit regularization of stochastic gradient flow for least squares
Article No.: 23, Pages 233–244

We study the implicit regularization of mini-batch stochastic gradient descent, when applied to the fundamental problem of least squares regression. We leverage a continuous-time stochastic differential equation having the same moments as stochastic ...

research-article
Free
Structural language models of code
Article No.: 24, Pages 245–256

We address the problem of any-code completion - generating a missing piece of source code in a given program without any restriction on the vocabulary or structure. We introduce a new approach to any-code completion that leverages the strict syntax of ...

research-article
Free
LowFER: low-rank bilinear pooling for link prediction
Article No.: 25, Pages 257–268

Knowledge graphs are incomplete by nature, with only a limited number of observed facts from the world knowledge being represented as structured relations between entities. To partly address this issue, an important task in statistical relational learning ...

research-article
Free
Discount factor as a regularizer in reinforcement learning
Article No.: 26, Pages 269–278

Specifying a Reinforcement Learning (RL) task involves choosing a suitable planning horizon, which is typically modeled by a discount factor. It is known that applying RL algorithms with a lower discount factor can act as a regularizer, improving ...

research-article
Free
Neuro-symbolic visual reasoning: disentangling "visual" from "reasoning"
Article No.: 27, Pages 279–290

Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However, recent advances in this area are still primarily driven by perception ...

research-article
Free
The differentiable cross-entropy method
Article No.: 28, Pages 291–302

We study the cross-entropy method (CEM) for the non-convex optimization of a continuous and parameterized objective function and introduce a differentiable variant that enables us to differentiate the output of CEM with respect to the objective function's ...

research-article
Free
Customizing ML predictions for online algorithms
Article No.: 29, Pages 303–313

A popular line of recent research incorporates ML advice in the design of online algorithms to improve their performance in typical instances. These papers treat the ML algorithm as a black-box, and redesign online algorithms to take advantage of ML ...

research-article
Free
Fairwashing explanations with off-manifold detergent
Article No.: 30, Pages 314–323

Explanation methods promise to make black-box classifiers more transparent. As a result, it is hoped that they can act as proof for a sensible, fair and trustworthy decision-making process of the algorithm and thereby increase its acceptance by the end-...

Contributors
  • University of Maryland, College Park

Index Terms

  1. Proceedings of the 37th International Conference on Machine Learning
    Index terms have been assigned to the content through auto-classification.
    Please enable JavaScript to view thecomments powered by Disqus.

    Recommendations