arXiv research

PriceAggregator optimizes hotel price fetching to increase Agoda's bookings.

Optimizes query routing to LLMs under cost and resource constraints.

New method tackles geodesically convex optimization with polynomial convergence.

sGPO optimizes RLVR training by balancing inference FLOPs and training efficiency.

Paper analyzes regret bounds for unconstrained online optimization.

LAZO reduces query complexity and variance in ZO methods.

Algorithm improves query recommendations with immediate user feedback.

We consider the problem of learning a general graph $G=(V,E)$ using edge-detecting queries, where the number of vertices $|V|=n$ is given to the learner. The information theoretic lower bound gives $m\log n$ for the number of queries, where $m=|E|$ is the number of edges. In case the number of edges $m$ is also given t…

Study learns linear utility functions from comparisons, showing learnability gaps between passive and active learning.

Causal discovery from empirical data is a fundamental problem in many scientific domains. Observational data allows for identifiability only up to Markov equivalence class. In this paper we first propose a polynomial time algorithm for learning the exact correctly-oriented structure of the transitive reduction of any c…

Budgeted deferral framework reduces expert query costs in machine learning.

Crowdsourced labeling recovers task types with minimal queries.

New framework infers multiple classes per image for one-shot learning.

Clustered attention improves transformer efficiency for large sequences.

We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available. On two public black-box attack challenges, the algorithm achieves the highest evasion rate, sur…

BILBO optimizes bilevel problems without repeated lower-level optimizations.

Efficiently tests two distributions with few label queries.

In query learning, the goal is to identify an unknown object while minimizing the number of "yes or no" questions (queries) posed about that object. We consider three extensions of this fundamental problem that are motivated by practical considerations in real-world, time-critical identification tasks such as emergency…

First-order stochastic methods are the state-of-the-art in large-scale machine learning optimization owing to efficient per-iteration complexity. Second-order methods, while able to provide faster convergence, have been much less explored due to the high cost of computing the second-order information. In this paper we …

In several recently proposed stochastic optimization methods (e.g. RMSProp, Adam, Adadelta), parameter updates are scaled by the inverse square roots of exponential moving averages of squared past gradients. Maintaining these per-parameter second-moment estimators requires memory equal to the number of parameters. For …

No-regret optimization for time-varying functions using uncertainty injection.

FEM improves attention mechanisms by applying value-driven log-linear tilts.

New method speeds up causal sensitivity analysis.

New algorithms reduce rejection sampling complexity for shape-constrained distributions.

New method tightens federated probe-logit distillation rates under varying bandwidths.

Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary by omitting probability scores, significantly impacting the utility of the provid…

New protocol identifies impossible edge orientations in causal graphs.

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only a few representatives of these classes. This problem has previously been approac…

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention lookup scale linearly in the size of the attended sequence. Second, it does not enc…

Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.

New insights into query complexity for Nash equilibrium learning.

Zeroth-order optimization is an important research topic in machine learning. In recent years, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract second-order information of the model function. In this…

Unified analysis of first-order methods for smooth games using IQCs.

Active learning has long been a topic of study in machine learning. However, as increasingly complex and opaque models have become standard practice, the process of active learning, too, has become more opaque. There has been little investigation into interpreting what specific trends and patterns an active learning st…

Paper develops an efficient mean estimator for 1-bit communication constraints.

ReOPD uses pre-collected teacher trajectories to distill knowledge from multi-turn interactions.

Online Active Learning (OAL) aims to manage unlabeled datastream by selectively querying the label of data. OAL is applicable to many real-world problems, such as anomaly detection in health-care and finance. In these problems, there are two key challenges: the query budget is often limited; the ratio between classes i…

Paper proposes ZO-NGD for more efficient black-box attacks.

New algorithm tackles dynamic query routing to multiple embedding models.

Learning to rank is a supervised learning problem where the output space is the space of rankings but the supervision space is the space of relevance scores. We make theoretical contributions to the learning to rank problem both in the online and batch settings. First, we propose a perceptron-like algorithm for learnin…

Investigates fast prediction rates with limited expert advice.

Understanding the 3-dimensional structure of the world is a core challenge in computer vision and robotics. Neural rendering approaches learn an implicit 3D model by predicting what a camera would see from an arbitrary viewpoint. We extend existing neural rendering to more complex, higher dimensional scenes than previo…

With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query it with their data via an API. However, if the user's input is sensitive, sending it to the server is undesirable and sometimes even legally …

New sampling algorithm for non-log-concave distributions requires many queries.

The paper establishes lower bounds for learning polynomial functions on hypercube.

COMRADE is a communication-efficient, Byzantine-resilient second-order optimization algorithm.

Deep Neural Networks, and specifically fully-connected convolutional neural networks are achieving remarkable results across a wide variety of domains. They have been trained to achieve state-of-the-art performance when applied to problems such as speech recognition, image classification, natural language processing an…