Papers made digestable
Our architecture simplifies the obstacle-perception
problem to that of place-dependent change detection. While we use the method with VT&R, it
can be generalized to suit arbitrary path-following applications.
Visual Teach and Repeat 3 (VT&R3), a generalization of stereo VT&R, achieves
long-term autonomous path-following using topometric mapping and localization
from a single rich sensor stream. In this paper, we improve the capabilities of
a LiDAR implementation of VT&R3 to reliably detect and avoid obstacles in
changing environments. Our architecture simplifies the obstacle-perception
problem to that of place-dependent change detection. We then extend the
behaviour of generic sample-based motion planners to better suit the
teach-and-repeat problem structure by introducing a new edge-cost metric paired
with a curvilinear planning space. The resulting planner generates naturally
smooth paths that avoid local obstacles while minimizing lateral path deviation
to best exploit prior terrain knowledge. While we use the method with VT&R, it
can be generalized to suit arbitrary path-following applications. Experimental
results from online run-time analysis, unit testing, and qualitative
experiments on a differential drive robot show the promise of the technique for
reliable long-term autonomous operation in complex unstructured environments.
Authors: Jordy Sehn, Yuchen Wu, Timothy D. Barfoot.
The statistical and design considerations that pertain to
dose optimization are discussed. The sample size savings range from 16.6% to 27.3%,
depending on the design and scenario, with a mean savings of 22.1%.
The traditional more-is-better dose selection paradigm, developed based on
cytotoxic chemotherapeutics, is often problematic When applied to the
development of novel molecularly targeted agents (e.g., kinase inhibitors,
monoclonal antibodies, and antibody-drug conjugates). The US Food and Drug
Administration (FDA) initiated Project Optimus to reform the dose optimization
and dose selection paradigm in oncology drug development and call for more
attention to benefit-risk consideration.
We systematically investigated the operating characteristics of the seamless
phase 2-3 design as a strategy for dose optimization, where in stage 1
(corresponding to phase 2) patients are randomized to multiple doses, with or
without a control; and in stage 2 (corresponding to phase 3) the efficacy of
the selected optimal dose is evaluated with a randomized concurrent control or
historical control. Depending on whether the concurrent control is included and
the type of endpoints used in stages 1 and 2, we describe four types of
seamless phase 2-3 dose-optimization designs, which are suitable for different
clinical settings. The statistical and design considerations that pertain to
dose optimization are discussed. Simulation shows that dose optimization phase
2-3 designs are able to control the familywise type I error rates and yield
appropriate statistical power with substantially smaller sample size than the
conventional approach. The sample size savings range from 16.6% to 27.3%,
depending on the design and scenario, with a mean savings of 22.1%. Due to the
interim dose selection, the phase 2-3 dose-optimization design is logistically
and operationally more challenging, and should be carefully planned and
implemented to ensure trial integrity.
Authors: Liyun Jiang, Ying Yuan.
We significantly improve performance using properties of the posterior
in our active learning scheme and for the definition of the GP prior. In
particular we account for the expected dynamical range of the posterior in
different dimensionalities. We test our model against a number of synthetic and
cosmological examples.
We present the GPry algorithm for fast Bayesian inference of general
(non-Gaussian) posteriors with a moderate number of parameters. GPry does not
need any pre-training, special hardware such as GPUs, and is intended as a
drop-in replacement for traditional Monte Carlo methods for Bayesian inference.
Our algorithm is based on generating a Gaussian Process surrogate model of the
log-posterior, aided by a Support Vector Machine classifier that excludes
extreme or non-finite values. An active learning scheme allows us to reduce the
number of required posterior evaluations by two orders of magnitude compared to
traditional Monte Carlo inference. Our algorithm allows for parallel
evaluations of the posterior at optimal locations, further reducing wall-clock
times. We significantly improve performance using properties of the posterior
in our active learning scheme and for the definition of the GP prior. In
particular we account for the expected dynamical range of the posterior in
different dimensionalities. We test our model against a number of synthetic and
cosmological examples. GPry outperforms traditional Monte Carlo methods when
the evaluation time of the likelihood (or the calculation of theoretical
observables) is of the order of seconds; for evaluation times of over a minute
it can perform inference in days that would take months using traditional
methods. GPry is distributed as an open source Python package (pip install
gpry) and can also be found at https://github.com/jonaselgammal/GPry.
Authors: Jonas El Gammal, Nils Schöneberg, Jesús Torrado, Christian Fidler.
We consider the fundamental scheduling problem of minimizing the sum of
weighted completion times on a single machine in the non-clairvoyant setting. However, to the best of our knowledge, this concept has never been considered
for the total completion time objective in the non-clairvoyant model. This implies
a performance guarantee of $(1+3\sqrt{3})\approx 6.197$ for the deterministic
algorithm and of $\approx 3.032$ for the randomized version.
We consider the fundamental scheduling problem of minimizing the sum of
weighted completion times on a single machine in the non-clairvoyant setting.
While no non-preemptive algorithm is constant competitive, Motwani, Phillips,
and Torng (SODA '93) proved that the simple preemptive round robin procedure is
$2$-competitive and that no better competitive ratio is possible, initiating a
long line of research focused on preemptive algorithms for generalized variants
of the problem. As an alternative model, Shmoys, Wein, and Williamson (FOCS
'91) introduced kill-and-restart schedules, where running jobs may be killed
and restarted from scratch later, and analyzed then for the makespan objective.
However, to the best of our knowledge, this concept has never been considered
for the total completion time objective in the non-clairvoyant model.
We contribute to both models: First we give for any $b > 1$ a tight analysis
for the natural $b$-scaling kill-and-restart strategy for scheduling jobs
without release dates, as well as for a randomized variant of it. This implies
a performance guarantee of $(1+3\sqrt{3})\approx 6.197$ for the deterministic
algorithm and of $\approx 3.032$ for the randomized version. Second, we show
that the preemptive Weighted Shortest Elapsed Time First (WSETF) rule is
$2$-competitive for jobs released in an online fashion over time, matching the
lower bound by Motwani et al. Using this result as well as the competitiveness
of round robin for multiple machines, we prove performance guarantees of
adaptions of the $b$-scaling algorithm to online release dates and unweighted
jobs on identical parallel machines.
Authors: Sven Jäger, Guillaume Sagnol, Daniel Schmidt genannt Waldschmidt, Philipp Warode.
Frozen pretrained models have become a viable alternative to the
pretraining-then-finetuning paradigm for transfer learning. With this work, we hope to
bring greater attention to this promising path of freezing pretrained image
models.
Frozen pretrained models have become a viable alternative to the
pretraining-then-finetuning paradigm for transfer learning. However, with
frozen models there are relatively few parameters available for adapting to
downstream tasks, which is problematic in computer vision where tasks vary
significantly in input/output format and the type of information that is of
value. In this paper, we present a study of frozen pretrained models when
applied to diverse and representative computer vision tasks, including object
detection, semantic segmentation and video action recognition. From this
empirical analysis, our work answers the questions of what pretraining task
fits best with this frozen setting, how to make the frozen setting more
flexible to various downstream tasks, and the effect of larger model sizes. We
additionally examine the upper bound of performance using a giant frozen
pretrained model with 3 billion parameters (SwinV2-G) and find that it reaches
competitive performance on a varied set of major benchmarks with only one
shared frozen base network: 60.0 box mAP and 52.2 mask mAP on COCO object
detection test-dev, 57.6 val mIoU on ADE20K semantic segmentation, and 81.7
top-1 accuracy on Kinetics-400 action recognition. With this work, we hope to
bring greater attention to this promising path of freezing pretrained image
models.
Authors: Yutong Lin, Ze Liu, Zheng Zhang, Han Hu, Nanning Zheng, Stephen Lin, Yue Cao.
Hence, strategies provide a convenient model of computations with
uninterpreted side-effects. Strategy models can be reformulated as
ideal completions of partial strategy trees (free dcpos on the term algebra). Extending the framework to multi-sorted signatures would make this construction
available for a large class of games.
I present a formal connection between algebraic effects and game semantics,
two important lines of work in programming languages semantics with
applications in compositional software verification.
Specifically, the algebraic signature enumerating the possible side-effects
of a computation can be read as a game, and strategies for this game constitute
the free algebra for the signature in a category of complete partial orders
(cpos). Hence, strategies provide a convenient model of computations with
uninterpreted side-effects. In particular, the operational flavor of game
semantics carries over to the algebraic context, in the form of the coincidence
between the initial algebras and the terminal coalgebras of cpo endofunctors.
Conversely, the algebraic point of view sheds new light on the strategy
constructions underlying game semantics. Strategy models can be reformulated as
ideal completions of partial strategy trees (free dcpos on the term algebra).
Extending the framework to multi-sorted signatures would make this construction
available for a large class of games.
Authors: Jérémie Koenig.
Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities can prevent disruptions and data bias in the state of an IoT application. The proposed framework is a lightweight and unsupervised implementation able to run on resource-constrained IoT devices. Our framework is also generalisable, adapting to new sensor streams and environments with minimal online reconfiguration.
Data integrity becomes paramount as the number of Internet of Things (IoT)
sensor deployments increases. Sensor data can be altered by benign causes or
malicious actions. Mechanisms that detect drifts and irregularities can prevent
disruptions and data bias in the state of an IoT application. This paper
presents LE3D, an ensemble framework of data drift estimators capable of
detecting abnormal sensor behaviours. Working collaboratively with surrounding
IoT devices, the type of drift (natural/abnormal) can also be identified and
reported to the end-user. The proposed framework is a lightweight and
unsupervised implementation able to run on resource-constrained IoT devices.
Our framework is also generalisable, adapting to new sensor streams and
environments with minimal online reconfiguration. We compare our method against
state-of-the-art ensemble data drift detection frameworks, evaluating both the
real-world detection accuracy as well as the resource utilisation of the
implementation. Experimenting with real-world data and emulated drifts, we show
the effectiveness of our method, which achieves up to 97% of detection accuracy
while requiring minimal resources to run.
Authors: Ioannis Mavromatis, Adrian Sanchez-Mompo, Francesco Raimondo, James Pope, Marcello Bullo, Ingram Weeks, Vijay Kumar, Pietro Carnelli, George Oikonomou, Theodoros Spyridopoulos, Aftab Khan.
However, these solutions usually
focus on visual data, and adapting them to the audio domain is not trivial. Moreover, it requires a separately trained model for every data sample. We show that our approach can reconstruct sound waves with quality
comparable to other state-of-the-art models.
Implicit neural representations (INRs) are a rapidly growing research field,
which provides alternative ways to represent multimedia signals. Recent
applications of INRs include image super-resolution, compression of
high-dimensional signals, or 3D rendering. However, these solutions usually
focus on visual data, and adapting them to the audio domain is not trivial.
Moreover, it requires a separately trained model for every data sample. To
address this limitation, we propose HyperSound, a meta-learning method
leveraging hypernetworks to produce INRs for audio signals unseen at training
time. We show that our approach can reconstruct sound waves with quality
comparable to other state-of-the-art models.
Authors: Filip Szatkowski, Karol J. Piczak, Przemysław Spurek, Jacek Tabor, Tomasz Trzciński.
No a priori Hilbert space is needed. OM admits an algebraic notion of operator expectation values without invoking states. $\psi_{KvN}$ and $\psi_{QM}$ are shown to be sections in ${\cal E}$. Rather, they both originate from a pre-quantum operator algebra.
We investigate operator algebraic origins of the classical Koopman-von
Neumann wave function $\psi_{KvN}$ as well as the quantum mechanical one
$\psi_{QM}$. We introduce a formalism of Operator Mechanics (OM) based on a
noncommutative Poisson, symplectic and noncommutative differential structures.
OM serves as a pre-quantum algebra from which algebraic structures relevant to
real-world classical and quantum mechanics follow. In particular, $\psi_{KvN}$
and $\psi_{QM}$ are both consequences of this pre-quantum formalism. No a
priori Hilbert space is needed. OM admits an algebraic notion of operator
expectation values without invoking states. A phase space bundle ${\cal E}$
follows from this. $\psi_{KvN}$ and $\psi_{QM}$ are shown to be sections in
${\cal E}$. The difference between $\psi_{KvN}$ and $\psi_{QM}$ originates from
a quantization map interpreted as "twisting" of sections over ${\cal E}$. We
also show that the Schr\"{o}dinger equation is obtained from the Koopman-von
Neumann equation. What this suggests is that neither the Schr\"{o}dinger
equation nor the quantum wave function are fundamental structures. Rather, they
both originate from a pre-quantum operator algebra.
Authors: Xerxes D. Arsiwalla, David Chester, Louis H. Kauffman.
can be
used to control text summarization. Unfortunately,
control signals are not already available during inference time. We also demonstrate generated summaries can
be controlled using prompts with user specified control tokens.
Prompts with different control signals (e.g., length, keywords, etc.) can be
used to control text summarization. When control signals are available, they
can control the properties of generated summaries and potentially improve
summarization quality (since more information are given). Unfortunately,
control signals are not already available during inference time. In this paper,
we propose Lotus (shorthand for Latent Prompt Tuning for Summarization), which
is a single model that can be applied in both controlled and uncontrolled
(without control signals) modes. During training, Lotus learns latent prompt
representations from prompts with gold control signals using a contrastive
learning objective. Experiments show Lotus in uncontrolled mode consistently
improves upon strong (uncontrollable) summarization models across four
different summarization datasets. We also demonstrate generated summaries can
be controlled using prompts with user specified control tokens.
Authors: Yubo Zhang, Xingxing Zhang, Xun Wang, Si-qing Chen, Furu Wei.
There are still some important unanswered questions about the unexpected very high energy $\gamma$-ray signatures. We suggest that energy spectral break in the few tens of TeV is a rough observational diagnostic for the LIV effects. The expected spectra characteristics are applied to a GRB 221009A.
There are still some important unanswered questions about the unexpected very
high energy $\gamma$-ray signatures. To help understand the mechanism, focusing
on the linear and quadratic perturbation mode for subliminal case, the present
paper revisited the expected signature for the Lorentz invariance violation
effects on $\gamma-\gamma$ absorption in TeV spectra of Gamma-ray bursts
(GRBs). We note that the existence of minimum photon energy threshold for the
pair production process leads up to a break energy, which is sensitive to the
quantum gravity energy scale. We suggest that energy spectral break in the few
tens of TeV is a rough observational diagnostic for the LIV effects. The
expected spectra characteristics are applied to a GRB 221009A. The results show
that the cosmic opacity with Lorentz invariance violation effects considered
here is able to roughly reproduce the observed $\gamma$-ray spectra for the
source, which enabled us to constrain the lower limit of the linear values of
energy scale at $E_{\rm QG,1}=3.35\times10^{20}$ GeV for the linear
perturbation and $E_{\rm QG,2}=9.19\times10^{13}$ GeV for the quadratic
perturbation. This value corresponds to a break energy $E_{\rm \gamma,
break,1}\simeq 55.95~\rm TeV$ for the linear and $E_{\rm \gamma, break,2}\simeq
73.66~\rm TeV$ for the quadratic in the observed frame respectively.
Authors: Y. G. Zheng, S. J. Kang, K. R. Zhu, C. Y. Yang, J. M. Bai.
There has recently been a desire to provide a
(coordinate-free) characterization of Jacobians and gradients in Cartesian
differential categories. As such, the Jacobian of a map is defined as the curry
of its derivative. We
also explain how a linearly closed Cartesian reverse differential category is
precisely a linearly closed Cartesian differential category with an appropriate
notion of transpose.
Cartesian differential categories come equipped with a differential
combinator that formalizes the directional derivative from multivariable
calculus. Cartesian differential categories provide a categorical semantics of
the differential lambda-calculus and have also found applications in causal
computation, incremental computation, game theory, differentiable programming,
and machine learning. There has recently been a desire to provide a
(coordinate-free) characterization of Jacobians and gradients in Cartesian
differential categories. One's first attempt might be to consider Cartesian
differential categories which are Cartesian closed, such as models of the
differential lambda-calculus, and then take the curry of the derivative.
Unfortunately, this approach excludes numerous important examples of Cartesian
differential categories such as the category of real smooth functions. In this
paper, we introduce linearly closed Cartesian differential categories, which
are Cartesian differential categories that have an internal hom of linear maps,
a bilinear evaluation map, and the ability to curry maps which are linear in
their second argument. As such, the Jacobian of a map is defined as the curry
of its derivative. Many well-known examples of Cartesian differential
categories are linearly closed, such as, in particular, the category of real
smooth functions. We also explain how a Cartesian closed differential category
is linearly closed if and only if a certain linear idempotent on the internal
hom splits. To define the gradient of a map, one must be able to define the
transpose of the Jacobian, which can be done in a Cartesian reverse
differential category. Thus, we define the gradient of a map to be the curry of
its reverse derivative and show this equals the transpose of its Jacobian. We
also explain how a linearly closed Cartesian reverse differential category is
precisely a linearly closed Cartesian differential category with an appropriate
notion of transpose.
Authors: Jean-Simon Pacaud Lemay.
In this work we propose ELECT, a new approach to select an effective candidate model, i.e. At its core, ELECT is based on meta-learning; transferring prior knowledge (e.g. model performance) on historical datasets that are similar to the new one to facilitate UOMS. Uniquely, it employs a dataset similarity measure that is performance-based, which is more direct and goal-driven than other measures used in the past.
Today there exists no shortage of outlier detection algorithms in the
literature, yet the complementary and critical problem of unsupervised outlier
model selection (UOMS) is vastly understudied. In this work we propose ELECT, a
new approach to select an effective candidate model, i.e. an outlier detection
algorithm and its hyperparameter(s), to employ on a new dataset without any
labels. At its core, ELECT is based on meta-learning; transferring prior
knowledge (e.g. model performance) on historical datasets that are similar to
the new one to facilitate UOMS. Uniquely, it employs a dataset similarity
measure that is performance-based, which is more direct and goal-driven than
other measures used in the past. ELECT adaptively searches for similar
historical datasets, as such, it can serve an output on-demand, being able to
accommodate varying time budgets. Extensive experiments show that ELECT
significantly outperforms a wide range of basic UOMS baselines, including no
model selection (always using the same popular model such as iForest) as well
as more recent selection strategies based on meta-features.
Authors: Yue Zhao, Sean Zhang, Leman Akoglu.
This work proposes a universal and adaptive second-order method for
minimizing second-order smooth, convex functions. Our algorithm achieves
$O(\sigma / \sqrt{T})$ convergence when the oracle feedback is stochastic with
variance $\sigma^2$, and improves its convergence to $O( 1 / T^3)$ with
deterministic oracles, where $T$ is the number of iterations. To our knowledge, this is the first universal algorithm with
such global guarantees within the second-order optimization literature.
This work proposes a universal and adaptive second-order method for
minimizing second-order smooth, convex functions. Our algorithm achieves
$O(\sigma / \sqrt{T})$ convergence when the oracle feedback is stochastic with
variance $\sigma^2$, and improves its convergence to $O( 1 / T^3)$ with
deterministic oracles, where $T$ is the number of iterations. Our method also
interpolates these rates without knowing the nature of the oracle apriori,
which is enabled by a parameter-free adaptive step-size that is oblivious to
the knowledge of smoothness modulus, variance bounds and the diameter of the
constrained set. To our knowledge, this is the first universal algorithm with
such global guarantees within the second-order optimization literature.
Authors: Kimon Antonakopoulos, Ali Kavis, Volkan Cevher.
We extend our earlier work on the compositional structure of cybernetic systems in order to account for the embodiment of such systems. We formalize this morphological perspective using polynomial functors.
We extend our earlier work on the compositional structure of cybernetic
systems in order to account for the embodiment of such systems. All their
interactions proceed through their bodies' boundaries: sensations impinge on
their surfaces, and actions correspond to changes in their configurations. We
formalize this morphological perspective using polynomial functors. The
'internal universes' of systems are shown to constitute an indexed category of
statistical games over polynomials; their dynamics form an indexed category of
behaviours. We characterize 'active inference doctrines' as indexed functors
between such categories, resolving a number of open problems in our earlier
work, and pointing to a formalization of the 'free energy principle' as adjoint
to such doctrines. We illustrate our framework through fundamental examples
from biology, including homeostasis, morphogenesis, and autopoiesis, and
suggest a formal connection between spatial navigation and the process of
proof.
Authors: Toby St Clere Smithe.